SlideShare a Scribd company logo
1 of 26
Download to read offline
© 2019 Your Company Name
Machine Learning Based Image
Compression: Ready for Prime Time?
Michael Gormish
Clarifai
May 2019
© 2019 Clarifai
What is Clarifai?
2
© 2019 Clarifai
Machine Learning is replacing traditional CV techniques
by using examples instead of equations
Image Classification
Image Segmentation
Object Detection
Image Matching
Pose Estimation
What about
Image Compression?
3
Difference of Gaussian, Histograms of Oriented
Gradients, Approximate Nearest Neighbors,
Fundamental Matrix
Label the input with the desired output
© 2019 Clarifai
Traditional Image Compression
Component Transform allows independent channel processing
Decorrelating transform - DCT for JPEG, Wavelet for JPEG 2000
Quantization - Quality Loss/Reduced File size
Entropy Coding - fully lossless
All very carefully selected and hand optimized to work together
4
© 2019 Clarifai
Traditional Image Compression Systems
GIF - string compressor on palletized image samples
PNG - string compressor on palletized or full range pixels
JPEG - block coder, Discrete Cosine Transform, Huffman Coding
JPEG 2000 - Tile coder, Wavelet Transform, Binary Entropy coder
H.264 - video block codec, supports stills
HEVC (H.265) - video block codec, supports stills
BPG - image block coder (HEVC subset)
XVC - proprietary video codec - with indemnification, supports stills
5
© 2019 Clarifai
Image Compression is a natural topic for ML
Vector quantization used in late 1980s
Auto-encoders are a common neural net topic
Don’t need to label millions of training samples (desired output = input)
6
© 2019 Clarifai
Modern ML methods show much better quality
But would you want these images?
7
GANs
© 2019 Clarifai
“Generative Compression” provides really small files
Compression changes content not
“quality” !!
But the system only works on
64x64 images and no code is
available
8
140:1
708:1
1416:1
[Santurkar, PCS 2018]
© 2019 Clarifai
TensorFlow provides Research models for compression
Improved Lossy Image Compression with Priming and Spatially
Adaptive Bit Rates for Recurrent Networks
Excellent Writeup and CODE!!!
Google: Nick Johnston, Damien Vincent, David
Minnen, Michele Covell, Saurabh Singh, Troy Chinen, Sung Jin
Hwang, Joel Shor, George Toderici
https://arxiv.org/abs/1703.10114
https://github.com/tensorflow/models/tree/master/research
/compression/image_encoder
http://download.tensorflow.org/models/
compression_residual_gru-2016-08-23.tar.gz
9
[Johnston CVPR 2018]
© 2019 Clarifai
JPEG artifacts
10
© 2019 Clarifai
0.125 bpp
0.250 bpp
ML artifacts
11
0.375 bpp
© 2019 Clarifai
ML provides more quality per bit
Peak Signal to Noise Ratio (PSNR) -
Higher is better
Structural Similarity (SSIM)
- Even bigger win for ML
12
Bits per pixel (bpp)
PSNR (Quality)
ML-Compression
JPEG-Compression
© 2019 Clarifai
ML Compression Has Better (and More) Basis Functions
More basis functions match the real world better
Higher level basis functions map to concepts
13
2-D 8x8 Discrete Cosine Transform
Four Levels of ML basis functions
© 2019 Clarifai
Computational Cost for More Basis Functions
2D DCT can be done with about 2 multiplies per (grayscale) pixel including quantization
A single 11x11 convolution layer with stride 4 will have 7.5 multiplies per pixel per channel per
kernel
A 4096 input 4096 output FC layer for a 224x224 input image is 326 multiplies per pixel
14
1D 8 Point DCT tranform 1D 8 Point 3 Layer Fully Connected
© 2019 Clarifai
JPEG 10,000x faster in totally unfair comparison
JPEG using one CPU core, ML code using 4 CPU cores of CPU
JPEG has been highly optimized, ML code was for demonstration purposes
Bit rates and quality were not matched
GPU/TPU/ASIC will speed up ML but how much energy savings will there be?
15
JPEG JPEG 2000 ML based
Encode Time
(ms)
26 217 292169
Decode Time
(ms)
12 157 208363
© 2019 Clarifai
CLIC 2018 - Workshop on ML image compression
Ranked by MS-SSIM (different from PSNR)
Top codec is 113x slower than jpeg (xvc and BPG are block coders)
Top codec is 97 Megabyte decoder (jpeg library might be 48K)
16
…
…
© 2019 Clarifai
Image Compression is often an interchange format
but…
Train on a different data set means need a new model at decoder
Many papers don’t have source code
Some only work on 64x64 images!!
Often only work at one or two bitrates
Some leave training as an exercise for the reader
17
© 2019 Clarifai
What can be done with ML in Embedded Systems
Embedded Camera? Do Machine Learned post-processing
Embedded Display? Do Machine Learned Preprocessing
18
© 2019 Clarifai
ML can be used to preprocess or post process
Machine learned image saliency can
guide a traditional block coder
(image top, saliency below)
Machine learned post processing
can improve block coded images
(jpeg decoded left, enhanced right)
19
[Galteri, ICCV 2017]
© 2019 Clarifai
Conclusion: Is ML based compression ready for prime
time?
Best quality per bit requires ML techniques especially at low bit rates
but
Computation/energy usage, and memory requirements are much higher
and
ML systems lack flexibility and interchange specification
therefore
NO.
Unless you have special use cases, e.g. special purpose ML HW available, but
very limited bandwidth (transmission cost/bandwidth)
20
© 2019 Clarifai
For Further Info
21
Papers
Preprocessing: Semantic Perceptual Image Compression using Deep Convolution Networks
https://arxiv.org/abs/1612.08712
Post Processing: Deep Generative Adversarial Compression Artifact Removal
http://openaccess.thecvf.com/content_ICCV_2017/papers/Galteri_Deep_Generative_Adver
sarial_ICCV_2017_paper.pdf
Evaluation of Compression
Kodak PhotoCD dataset.
http://r0k.us/graphics/kodak
CLIC - Workshop and Challenge on Learned Image Compression
http://www.compression.cc/
MS SSIM - Multi-scale structural Similarity for Image Quality Assessment
http://www.cns.nyu.edu/~zwang/files/papers/msssim.pdf
© 2019 Your Company Name
Backup Material
22
© 2019 Clarifai
References
23
© 2019 Clarifai
Clarifai Platform
24
© 2019 Clarifai
About Clarifai
25
© 2019 Clarifai
Clarifai Models
26

More Related Content

What's hot

Introducing google’s mobile nets
Introducing google’s mobile netsIntroducing google’s mobile nets
Introducing google’s mobile netsLarry Guo
 
Presentation
PresentationPresentation
Presentationbutest
 
Imaging automotive 2015 addfor v002
Imaging automotive 2015   addfor v002Imaging automotive 2015   addfor v002
Imaging automotive 2015 addfor v002Enrico Busto
 
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...Edge AI and Vision Alliance
 
"End to End Fire Detection Deep Neural Network Platform," a Presentation from...
"End to End Fire Detection Deep Neural Network Platform," a Presentation from..."End to End Fire Detection Deep Neural Network Platform," a Presentation from...
"End to End Fire Detection Deep Neural Network Platform," a Presentation from...Edge AI and Vision Alliance
 
A SURVEY OF NEURAL NETWORK HARDWARE ACCELERATORS IN MACHINE LEARNING
A SURVEY OF NEURAL NETWORK HARDWARE ACCELERATORS IN MACHINE LEARNING A SURVEY OF NEURAL NETWORK HARDWARE ACCELERATORS IN MACHINE LEARNING
A SURVEY OF NEURAL NETWORK HARDWARE ACCELERATORS IN MACHINE LEARNING mlaij
 
Enabling Power-Efficient AI Through Quantization
Enabling Power-Efficient AI Through QuantizationEnabling Power-Efficient AI Through Quantization
Enabling Power-Efficient AI Through QuantizationQualcomm Research
 
Deep learning for smart manufacturing
Deep learning for smart manufacturingDeep learning for smart manufacturing
Deep learning for smart manufacturingSunil Kumar Pradhan
 
"Approaches for Energy Efficient Implementation of Deep Neural Networks," a P...
"Approaches for Energy Efficient Implementation of Deep Neural Networks," a P..."Approaches for Energy Efficient Implementation of Deep Neural Networks," a P...
"Approaches for Energy Efficient Implementation of Deep Neural Networks," a P...Edge AI and Vision Alliance
 
"Designing a Stereo IP Camera From Scratch," a Presentation from ELVEES
"Designing a Stereo IP Camera From Scratch," a Presentation from ELVEES"Designing a Stereo IP Camera From Scratch," a Presentation from ELVEES
"Designing a Stereo IP Camera From Scratch," a Presentation from ELVEESEdge AI and Vision Alliance
 
Dataset Culling: Towards Efficient Training of Distillation based Domain Spec...
Dataset Culling: Towards Efficient Training of Distillation based Domain Spec...Dataset Culling: Towards Efficient Training of Distillation based Domain Spec...
Dataset Culling: Towards Efficient Training of Distillation based Domain Spec...Kentaro Yoshioka
 
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...Edge AI and Vision Alliance
 
Near Data Computing Architectures: Opportunities and Challenges for Apache Spark
Near Data Computing Architectures: Opportunities and Challenges for Apache SparkNear Data Computing Architectures: Opportunities and Challenges for Apache Spark
Near Data Computing Architectures: Opportunities and Challenges for Apache SparkAhsan Javed Awan
 
A Survey of Machine Learning Methods Applied to Computer ...
A Survey of Machine Learning Methods Applied to Computer ...A Survey of Machine Learning Methods Applied to Computer ...
A Survey of Machine Learning Methods Applied to Computer ...butest
 
“Applying the Right Deep Learning Model with the Right Data for Your Applicat...
“Applying the Right Deep Learning Model with the Right Data for Your Applicat...“Applying the Right Deep Learning Model with the Right Data for Your Applicat...
“Applying the Right Deep Learning Model with the Right Data for Your Applicat...Edge AI and Vision Alliance
 
"Designing CNN Algorithms for Real-time Applications," a Presentation from Al...
"Designing CNN Algorithms for Real-time Applications," a Presentation from Al..."Designing CNN Algorithms for Real-time Applications," a Presentation from Al...
"Designing CNN Algorithms for Real-time Applications," a Presentation from Al...Edge AI and Vision Alliance
 
An AI accelerator ASIC architecture
An AI accelerator ASIC architectureAn AI accelerator ASIC architecture
An AI accelerator ASIC architectureKhanh Le
 
Scaling up deep learning by scaling down
Scaling up deep learning by scaling downScaling up deep learning by scaling down
Scaling up deep learning by scaling downNick Pentreath
 
“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...
“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...
“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...Edge AI and Vision Alliance
 
“Getting Started with Vision AI Model Training,” a Presentation from NVIDIA
“Getting Started with Vision AI Model Training,” a Presentation from NVIDIA“Getting Started with Vision AI Model Training,” a Presentation from NVIDIA
“Getting Started with Vision AI Model Training,” a Presentation from NVIDIAEdge AI and Vision Alliance
 

What's hot (20)

Introducing google’s mobile nets
Introducing google’s mobile netsIntroducing google’s mobile nets
Introducing google’s mobile nets
 
Presentation
PresentationPresentation
Presentation
 
Imaging automotive 2015 addfor v002
Imaging automotive 2015   addfor v002Imaging automotive 2015   addfor v002
Imaging automotive 2015 addfor v002
 
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
 
"End to End Fire Detection Deep Neural Network Platform," a Presentation from...
"End to End Fire Detection Deep Neural Network Platform," a Presentation from..."End to End Fire Detection Deep Neural Network Platform," a Presentation from...
"End to End Fire Detection Deep Neural Network Platform," a Presentation from...
 
A SURVEY OF NEURAL NETWORK HARDWARE ACCELERATORS IN MACHINE LEARNING
A SURVEY OF NEURAL NETWORK HARDWARE ACCELERATORS IN MACHINE LEARNING A SURVEY OF NEURAL NETWORK HARDWARE ACCELERATORS IN MACHINE LEARNING
A SURVEY OF NEURAL NETWORK HARDWARE ACCELERATORS IN MACHINE LEARNING
 
Enabling Power-Efficient AI Through Quantization
Enabling Power-Efficient AI Through QuantizationEnabling Power-Efficient AI Through Quantization
Enabling Power-Efficient AI Through Quantization
 
Deep learning for smart manufacturing
Deep learning for smart manufacturingDeep learning for smart manufacturing
Deep learning for smart manufacturing
 
"Approaches for Energy Efficient Implementation of Deep Neural Networks," a P...
"Approaches for Energy Efficient Implementation of Deep Neural Networks," a P..."Approaches for Energy Efficient Implementation of Deep Neural Networks," a P...
"Approaches for Energy Efficient Implementation of Deep Neural Networks," a P...
 
"Designing a Stereo IP Camera From Scratch," a Presentation from ELVEES
"Designing a Stereo IP Camera From Scratch," a Presentation from ELVEES"Designing a Stereo IP Camera From Scratch," a Presentation from ELVEES
"Designing a Stereo IP Camera From Scratch," a Presentation from ELVEES
 
Dataset Culling: Towards Efficient Training of Distillation based Domain Spec...
Dataset Culling: Towards Efficient Training of Distillation based Domain Spec...Dataset Culling: Towards Efficient Training of Distillation based Domain Spec...
Dataset Culling: Towards Efficient Training of Distillation based Domain Spec...
 
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
 
Near Data Computing Architectures: Opportunities and Challenges for Apache Spark
Near Data Computing Architectures: Opportunities and Challenges for Apache SparkNear Data Computing Architectures: Opportunities and Challenges for Apache Spark
Near Data Computing Architectures: Opportunities and Challenges for Apache Spark
 
A Survey of Machine Learning Methods Applied to Computer ...
A Survey of Machine Learning Methods Applied to Computer ...A Survey of Machine Learning Methods Applied to Computer ...
A Survey of Machine Learning Methods Applied to Computer ...
 
“Applying the Right Deep Learning Model with the Right Data for Your Applicat...
“Applying the Right Deep Learning Model with the Right Data for Your Applicat...“Applying the Right Deep Learning Model with the Right Data for Your Applicat...
“Applying the Right Deep Learning Model with the Right Data for Your Applicat...
 
"Designing CNN Algorithms for Real-time Applications," a Presentation from Al...
"Designing CNN Algorithms for Real-time Applications," a Presentation from Al..."Designing CNN Algorithms for Real-time Applications," a Presentation from Al...
"Designing CNN Algorithms for Real-time Applications," a Presentation from Al...
 
An AI accelerator ASIC architecture
An AI accelerator ASIC architectureAn AI accelerator ASIC architecture
An AI accelerator ASIC architecture
 
Scaling up deep learning by scaling down
Scaling up deep learning by scaling downScaling up deep learning by scaling down
Scaling up deep learning by scaling down
 
“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...
“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...
“Explainability in Computer Vision: A Machine Learning Engineer’s Overview,” ...
 
“Getting Started with Vision AI Model Training,” a Presentation from NVIDIA
“Getting Started with Vision AI Model Training,” a Presentation from NVIDIA“Getting Started with Vision AI Model Training,” a Presentation from NVIDIA
“Getting Started with Vision AI Model Training,” a Presentation from NVIDIA
 

Similar to "Machine Learning- based Image Compression: Ready for Prime Time?," a Presentation from Clarifai

A Novel Approach for Compressing Surveillance System Videos
A Novel Approach for Compressing Surveillance System VideosA Novel Approach for Compressing Surveillance System Videos
A Novel Approach for Compressing Surveillance System VideosINFOGAIN PUBLICATION
 
RESPONSIVE VIDEO FORMAT FOR ADAPTIVE STREAMING
RESPONSIVE VIDEO FORMAT FOR ADAPTIVE STREAMINGRESPONSIVE VIDEO FORMAT FOR ADAPTIVE STREAMING
RESPONSIVE VIDEO FORMAT FOR ADAPTIVE STREAMINGJournal For Research
 
Seminar Report on image compression
Seminar Report on image compressionSeminar Report on image compression
Seminar Report on image compressionPradip Kumar
 
Technical file
Technical fileTechnical file
Technical filesamgh1995
 
Technical glossary
Technical glossaryTechnical glossary
Technical glossaryAmaanGDesign
 
Project presentation image compression by manish myst, ssgbcoet
Project presentation image compression by manish myst, ssgbcoetProject presentation image compression by manish myst, ssgbcoet
Project presentation image compression by manish myst, ssgbcoetManish Myst
 
Performance and Memory Tuning - Part III - Transcript.pdf
Performance and Memory Tuning - Part III - Transcript.pdfPerformance and Memory Tuning - Part III - Transcript.pdf
Performance and Memory Tuning - Part III - Transcript.pdfShaiAlmog1
 
Reduction of Blocking Artifacts In JPEG Compressed Image
Reduction of Blocking Artifacts In JPEG Compressed ImageReduction of Blocking Artifacts In JPEG Compressed Image
Reduction of Blocking Artifacts In JPEG Compressed ImageDr Sukhpal Singh Gill
 
Video compression
Video compressionVideo compression
Video compressionDeepa K C
 
Task 1 technical file
Task 1   technical fileTask 1   technical file
Task 1 technical fileNathan_West
 
Image Processing in Android Environment AJCSE
Image Processing in Android Environment AJCSEImage Processing in Android Environment AJCSE
Image Processing in Android Environment AJCSEBRNSSPublicationHubI
 
Patch-Based Image Learned Codec using Overlapping
Patch-Based Image Learned Codec using OverlappingPatch-Based Image Learned Codec using Overlapping
Patch-Based Image Learned Codec using Overlappingsipij
 
FLIF, a new lossless image file format
FLIF, a new lossless image file formatFLIF, a new lossless image file format
FLIF, a new lossless image file formatKashyap Kotak
 
FLIF, a new lossless image file format
FLIF, a new lossless image file formatFLIF, a new lossless image file format
FLIF, a new lossless image file formatKashyap Kotak
 

Similar to "Machine Learning- based Image Compression: Ready for Prime Time?," a Presentation from Clarifai (20)

A Novel Approach for Compressing Surveillance System Videos
A Novel Approach for Compressing Surveillance System VideosA Novel Approach for Compressing Surveillance System Videos
A Novel Approach for Compressing Surveillance System Videos
 
RESPONSIVE VIDEO FORMAT FOR ADAPTIVE STREAMING
RESPONSIVE VIDEO FORMAT FOR ADAPTIVE STREAMINGRESPONSIVE VIDEO FORMAT FOR ADAPTIVE STREAMING
RESPONSIVE VIDEO FORMAT FOR ADAPTIVE STREAMING
 
Seminar Report on image compression
Seminar Report on image compressionSeminar Report on image compression
Seminar Report on image compression
 
Technical file
Technical fileTechnical file
Technical file
 
Technical glossary
Technical glossaryTechnical glossary
Technical glossary
 
Project presentation image compression by manish myst, ssgbcoet
Project presentation image compression by manish myst, ssgbcoetProject presentation image compression by manish myst, ssgbcoet
Project presentation image compression by manish myst, ssgbcoet
 
Open power ddl and lms
Open power ddl and lmsOpen power ddl and lms
Open power ddl and lms
 
Performance and Memory Tuning - Part III - Transcript.pdf
Performance and Memory Tuning - Part III - Transcript.pdfPerformance and Memory Tuning - Part III - Transcript.pdf
Performance and Memory Tuning - Part III - Transcript.pdf
 
Image Optimization
Image OptimizationImage Optimization
Image Optimization
 
BSC LMS DDL
BSC LMS DDL BSC LMS DDL
BSC LMS DDL
 
Reduction of Blocking Artifacts In JPEG Compressed Image
Reduction of Blocking Artifacts In JPEG Compressed ImageReduction of Blocking Artifacts In JPEG Compressed Image
Reduction of Blocking Artifacts In JPEG Compressed Image
 
Video compression
Video compressionVideo compression
Video compression
 
Bmsc1103
Bmsc1103Bmsc1103
Bmsc1103
 
madhu
madhumadhu
madhu
 
Task 1 technical file
Task 1   technical fileTask 1   technical file
Task 1 technical file
 
Image Processing in Android Environment AJCSE
Image Processing in Android Environment AJCSEImage Processing in Android Environment AJCSE
Image Processing in Android Environment AJCSE
 
Jpack presentation
Jpack presentationJpack presentation
Jpack presentation
 
Patch-Based Image Learned Codec using Overlapping
Patch-Based Image Learned Codec using OverlappingPatch-Based Image Learned Codec using Overlapping
Patch-Based Image Learned Codec using Overlapping
 
FLIF, a new lossless image file format
FLIF, a new lossless image file formatFLIF, a new lossless image file format
FLIF, a new lossless image file format
 
FLIF, a new lossless image file format
FLIF, a new lossless image file formatFLIF, a new lossless image file format
FLIF, a new lossless image file format
 

More from Edge AI and Vision Alliance

“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...Edge AI and Vision Alliance
 
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...Edge AI and Vision Alliance
 
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...Edge AI and Vision Alliance
 
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...Edge AI and Vision Alliance
 
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...Edge AI and Vision Alliance
 
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...Edge AI and Vision Alliance
 
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...Edge AI and Vision Alliance
 
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsightsEdge AI and Vision Alliance
 
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...Edge AI and Vision Alliance
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...Edge AI and Vision Alliance
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...Edge AI and Vision Alliance
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...Edge AI and Vision Alliance
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...Edge AI and Vision Alliance
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...Edge AI and Vision Alliance
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...Edge AI and Vision Alliance
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from SamsaraEdge AI and Vision Alliance
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...Edge AI and Vision Alliance
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...Edge AI and Vision Alliance
 
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...Edge AI and Vision Alliance
 
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...Edge AI and Vision Alliance
 

More from Edge AI and Vision Alliance (20)

“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
 
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
 
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
 
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
 
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
 
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
 
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...
 
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
 
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
 
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
 
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
 

Recently uploaded

Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxnull - The Open Security Community
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhisoniya singh
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxOnBoard
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksSoftradix Technologies
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
Unlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power SystemsUnlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power SystemsPrecisely
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024BookNet Canada
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 

Recently uploaded (20)

Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptx
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other Frameworks
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
Unlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power SystemsUnlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power Systems
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 

"Machine Learning- based Image Compression: Ready for Prime Time?," a Presentation from Clarifai

  • 1. © 2019 Your Company Name Machine Learning Based Image Compression: Ready for Prime Time? Michael Gormish Clarifai May 2019
  • 2. © 2019 Clarifai What is Clarifai? 2
  • 3. © 2019 Clarifai Machine Learning is replacing traditional CV techniques by using examples instead of equations Image Classification Image Segmentation Object Detection Image Matching Pose Estimation What about Image Compression? 3 Difference of Gaussian, Histograms of Oriented Gradients, Approximate Nearest Neighbors, Fundamental Matrix Label the input with the desired output
  • 4. © 2019 Clarifai Traditional Image Compression Component Transform allows independent channel processing Decorrelating transform - DCT for JPEG, Wavelet for JPEG 2000 Quantization - Quality Loss/Reduced File size Entropy Coding - fully lossless All very carefully selected and hand optimized to work together 4
  • 5. © 2019 Clarifai Traditional Image Compression Systems GIF - string compressor on palletized image samples PNG - string compressor on palletized or full range pixels JPEG - block coder, Discrete Cosine Transform, Huffman Coding JPEG 2000 - Tile coder, Wavelet Transform, Binary Entropy coder H.264 - video block codec, supports stills HEVC (H.265) - video block codec, supports stills BPG - image block coder (HEVC subset) XVC - proprietary video codec - with indemnification, supports stills 5
  • 6. © 2019 Clarifai Image Compression is a natural topic for ML Vector quantization used in late 1980s Auto-encoders are a common neural net topic Don’t need to label millions of training samples (desired output = input) 6
  • 7. © 2019 Clarifai Modern ML methods show much better quality But would you want these images? 7 GANs
  • 8. © 2019 Clarifai “Generative Compression” provides really small files Compression changes content not “quality” !! But the system only works on 64x64 images and no code is available 8 140:1 708:1 1416:1 [Santurkar, PCS 2018]
  • 9. © 2019 Clarifai TensorFlow provides Research models for compression Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks Excellent Writeup and CODE!!! Google: Nick Johnston, Damien Vincent, David Minnen, Michele Covell, Saurabh Singh, Troy Chinen, Sung Jin Hwang, Joel Shor, George Toderici https://arxiv.org/abs/1703.10114 https://github.com/tensorflow/models/tree/master/research /compression/image_encoder http://download.tensorflow.org/models/ compression_residual_gru-2016-08-23.tar.gz 9 [Johnston CVPR 2018]
  • 10. © 2019 Clarifai JPEG artifacts 10
  • 11. © 2019 Clarifai 0.125 bpp 0.250 bpp ML artifacts 11 0.375 bpp
  • 12. © 2019 Clarifai ML provides more quality per bit Peak Signal to Noise Ratio (PSNR) - Higher is better Structural Similarity (SSIM) - Even bigger win for ML 12 Bits per pixel (bpp) PSNR (Quality) ML-Compression JPEG-Compression
  • 13. © 2019 Clarifai ML Compression Has Better (and More) Basis Functions More basis functions match the real world better Higher level basis functions map to concepts 13 2-D 8x8 Discrete Cosine Transform Four Levels of ML basis functions
  • 14. © 2019 Clarifai Computational Cost for More Basis Functions 2D DCT can be done with about 2 multiplies per (grayscale) pixel including quantization A single 11x11 convolution layer with stride 4 will have 7.5 multiplies per pixel per channel per kernel A 4096 input 4096 output FC layer for a 224x224 input image is 326 multiplies per pixel 14 1D 8 Point DCT tranform 1D 8 Point 3 Layer Fully Connected
  • 15. © 2019 Clarifai JPEG 10,000x faster in totally unfair comparison JPEG using one CPU core, ML code using 4 CPU cores of CPU JPEG has been highly optimized, ML code was for demonstration purposes Bit rates and quality were not matched GPU/TPU/ASIC will speed up ML but how much energy savings will there be? 15 JPEG JPEG 2000 ML based Encode Time (ms) 26 217 292169 Decode Time (ms) 12 157 208363
  • 16. © 2019 Clarifai CLIC 2018 - Workshop on ML image compression Ranked by MS-SSIM (different from PSNR) Top codec is 113x slower than jpeg (xvc and BPG are block coders) Top codec is 97 Megabyte decoder (jpeg library might be 48K) 16 … …
  • 17. © 2019 Clarifai Image Compression is often an interchange format but… Train on a different data set means need a new model at decoder Many papers don’t have source code Some only work on 64x64 images!! Often only work at one or two bitrates Some leave training as an exercise for the reader 17
  • 18. © 2019 Clarifai What can be done with ML in Embedded Systems Embedded Camera? Do Machine Learned post-processing Embedded Display? Do Machine Learned Preprocessing 18
  • 19. © 2019 Clarifai ML can be used to preprocess or post process Machine learned image saliency can guide a traditional block coder (image top, saliency below) Machine learned post processing can improve block coded images (jpeg decoded left, enhanced right) 19 [Galteri, ICCV 2017]
  • 20. © 2019 Clarifai Conclusion: Is ML based compression ready for prime time? Best quality per bit requires ML techniques especially at low bit rates but Computation/energy usage, and memory requirements are much higher and ML systems lack flexibility and interchange specification therefore NO. Unless you have special use cases, e.g. special purpose ML HW available, but very limited bandwidth (transmission cost/bandwidth) 20
  • 21. © 2019 Clarifai For Further Info 21 Papers Preprocessing: Semantic Perceptual Image Compression using Deep Convolution Networks https://arxiv.org/abs/1612.08712 Post Processing: Deep Generative Adversarial Compression Artifact Removal http://openaccess.thecvf.com/content_ICCV_2017/papers/Galteri_Deep_Generative_Adver sarial_ICCV_2017_paper.pdf Evaluation of Compression Kodak PhotoCD dataset. http://r0k.us/graphics/kodak CLIC - Workshop and Challenge on Learned Image Compression http://www.compression.cc/ MS SSIM - Multi-scale structural Similarity for Image Quality Assessment http://www.cns.nyu.edu/~zwang/files/papers/msssim.pdf
  • 22. © 2019 Your Company Name Backup Material 22
  • 25. © 2019 Clarifai About Clarifai 25