SlideShare a Scribd company logo
Tips and tricks for building your own
automated visual data annotation
systems
Sr ML Engineer at Depositphotos
AI&BigData Online Day 2022
About me
❏ Yurii Pashchenko
❏ Sr Machine Learning Engineer at Depositphotos
❏ Over 9 years of research and commercial experience in
applying Deep Learning models
❏ Object Detection and Face Recognition Specialist
Tips and tricks for building your own automated
visual data annotation systems
❏ What is data annotation
❏ Types of visual data annotation
❏ Why data annotation is so important
❏ Challenges in the Image Annotation process
❏ Computer Vision Open Source libraries
❏ Annotation of novel classes
❏ Relevant Sample Search
❏ Zero-Shot Classification
❏ Few-Shot Semantic Segmentation
❏ Open-Vocabulary Object Detection
What is data annotation
“Computers can't process visual information the way human brains do: A computer
needs to be told what it's interpreting and provided context in order to make decisions.
Data annotation makes those connections.
It's the human-led task of labeling content such as text, audio, images and video so it
can be recognized by machine learning models and used to make predictions.”
What is data annotation and why does it matter?
Why it so important
● Data is the backbone of the customer experience. How well you know your
clients directly impacts the quality of their experiences.
● Noticeable correlation between correctly annotated data and the success of
the project
● As much as image annotated data is used to train the machine learning model,
the accuracy will be higher.
● If you are working on an unsupervised machine learning project, sooner or
later, you might need to have data annotation work done if you want to reach
better performance of the algorithms.
Challenges in the Image Annotation Process
Balancing costs with accuracy levels: There are two primary data annotation methods—human annotation and
automated annotation. Human annotation typically takes longer and costs more than automated annotation, and also
requires training for annotators, but achieves more accurate results. In comparison, automated annotation is more
cost-effective but it can be difficult to determine the accuracy level of the results.
Guaranteeing consistent data: Machine learning models need a good quality of consistent data to make accurate
predictions. However, data labelers may interpret subjective data differently due to their beliefs, culture, and personal
biases. If data is labeled inconsistently, the results of a machine learning model will also be skewed.
Choosing a suitable annotation tool: There are many image annotation platforms and tools, each providing
different capabilities for different types of annotations. The variety of offerings can make it difficult to choose the
most suitable tools for each project. It can also be challenging to choose the right tool to match the skillsets of your
workforce.
Image Annotation for Computer Vision: A Practical Guide
Available annotation tools
1. V7
2. Labelbox
3. Scale AI
4. SuperAnnotate
5. Dataloop
6. Playment
7. Supervise.ly
8. Hive Data
9. CVAT
10. LabelMe
11. LabeIimg
12. VoTT
13. Img Lab
13 Best Image Annotation Tools of 2022
Tips and tricks for building your own automated
visual data annotation systems
❏ What is data annotation
❏ Types of visual data annotation
❏ Why data annotation is so important
❏ Challenges in the Image Annotation process
❏ Computer Vision Open Source libraries
❏ Annotation of novel classes
❏ Relevant Sample Search
❏ Zero-Shot Classification
❏ Object Detection/Segmentation
❏ Few-Shot Semantic Segmentation
❏ Open-Vocabulary Object Detection
Detectron2
Detectron2
● Facebook AI
● Various tasks
● Unified configs
● Inference speed (fast)
OpenMMLab
● Modular Design
● Support of multiple
frameworks out of the box
● High efficiency
● State of the art
OpenMMLab
Tips and tricks for building your own automated
visual data annotation systems
❏ What is data annotation
❏ Types of visual data annotation
❏ Why data annotation is so important
❏ Challenges in the Image Annotation process
❏ Computer Vision Open Source libraries
❏ Annotation of novel classes
❏ Relevant Sample Search
❏ Zero-Shot Classification
❏ Object Detection/Segmentation
❏ Few-Shot Semantic Segmentation
❏ Open-Vocabulary Object Detection
Relevant image search
Image search engine using Deep Learning Model
Relevant image search
Recipe:
1. Preparation
a. Convert images to 224x224x3
b. Extract features by VGG16 model of
size 4096
c. Store embeddings
2. Comparison
a. Extract features for reference image
b. Compute distance (cosine) between
input feature and all embeddings in
dataset
c. Sort distances in ascending order
d. Show first k-images
Image search engine using Deep Learning Model
Limitations:
● only for similarity search
● features are not representative
on real-world samples
● Applicable for datasets 1-10K in
terms of speed
Tips and tricks for building your own automated
visual data annotation systems
❏ What is data annotation
❏ Types of visual data annotation
❏ Challenges in the Image Annotation process
❏ Why data annotation is so important
❏ Computer Vision Open Source libraries
❏ Annotation of novel classes
❏ Relevant Sample Search
❏ Zero-Shot Classification
❏ Object Detection/Segmentation
❏ Few-Shot Semantic Segmentation
❏ Open-Vocabulary Object Detection
CLIP: Contrastive Language-Image Pre-training
Learning Transferable Visual Models From Natural Language Supervision
● 400 million (image, text) pairs collected
from Internet.
● Trained modifications of ResNet-50
and ViT-B
● Batch size 32 768 for 32 epochs
● The largest ResNet model, RN50x64,
took 18 days to train on 592 V100
GPUs while the largest Vision
Transformer took 12 days on 256
V100 GPUs
CLIP for Zero-Shot Classification
Learning Transferable Visual Models From Natural Language Supervision
Ensembling around 80
prompts improve
ImageNet accuracy by
almost 5%
Facebook AI Similarity Search (FAISS)
Faiss: A library for efficient similarity search
CLIP-based Image Search
Text-to-Image
Unsplash Image Search
"Two dogs playing in the snow"
“The world love written on the wall”
“The feeling when your program
finally works”
CLIP-based for Image Search
Image+Text-to-Image
Unsplash Image Search
+
“cars”
Tips and tricks for building your own automated
visual data annotation systems
❏ What is data annotation
❏ Types of visual data annotation
❏ Challenges in the Image Annotation process
❏ Why data annotation is so important
❏ Computer Vision Open Source libraries
❏ Annotation of novel classes
❏ Relevant Sample Search
❏ Zero-Shot Classification
❏ Object Detection/Segmentation
❏ Few-Shot Semantic Segmentation
❏ Open-Vocabulary Object Detection
You can’t just make an Object Detector
from a Classifier
… without fine-tuning
Assembling Object Detector with CLIP
Rich feature hierarchies for accurate object detection and semantic segmentation
CLIP
Text
Encoder
person
Region proposals alternatives
Salient Object Detection Techniques in Computer Vision—A Survey
Salient object detection (SOD) is an important computer vision task aimed at precise
detection and segmentation of visually distinctive image regions from the perspective of the
human visual system
Region proposals alternatives
Open-World Entity Segmentation
Entity Segmentation is a segmentation task with the aim to segment everything in an image
into semantically-meaningful regions without considering any category labels.
Tips and tricks for building your own automated
visual data annotation systems
❏ What is data annotation
❏ Types of visual data annotation
❏ Challenges in the Image Annotation process
❏ Why data annotation is so important
❏ Computer Vision Open Source libraries
❏ Annotation of novel classes
❏ Relevant Sample Search
❏ Zero-Shot Classification
❏ Object Detection/Segmentation
❏ Few-Shot Semantic Segmentation
❏ Open-Vocabulary Object Detection
Few-Shot Semantic Segmentation
MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation
Few-Shot Semantic Segmentation
MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation
Tips and tricks for building your own automated
visual data annotation systems
❏ What is data annotation
❏ Types of visual data annotation
❏ Challenges in the Image Annotation process
❏ Why data annotation is so important
❏ Computer Vision Open Source libraries
❏ Annotation of novel classes
❏ Relevant Sample Search
❏ Zero-Shot Classification
❏ Object Detection/Segmentation
❏ Few-Shot Semantic Segmentation
❏ Open-Vocabulary Object Detection
Open Vocabulary Object Detection
https://paperswithcode.com/task/open-vocabulary-object-detection/latest
Open-vocabulary detection (OVD) aims to generalize beyond the limited number of base classes labeled during the
training phase. The goal is to detect novel classes defined by an unbounded (open) vocabulary at inference
Vision and Language knowledge Distillation
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
VILD generalization ability
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
VILD visualizations
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
VILD visualizations
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
Is it worth it?
Thank you for your attention!
Yurii Pashchenko AI&BigData Online Day 2022
Yurii Pashchenko
Sr ML Engineer at Depositphotos
yurii_pas
george.pashchenko@gmail.com

More Related Content

Similar to Yurii Pashchenko: Tips and tricks for building your own automated visual data annotation system

From c# Into Machine Learning
From c# Into Machine LearningFrom c# Into Machine Learning
From c# Into Machine Learning
Dev Raj Gautam
 
AI for Software Engineering
AI for Software EngineeringAI for Software Engineering
AI for Software Engineering
Miroslaw Staron
 
Data Workflows for Machine Learning - Seattle DAML
Data Workflows for Machine Learning - Seattle DAMLData Workflows for Machine Learning - Seattle DAML
Data Workflows for Machine Learning - Seattle DAML
Paco Nathan
 
OpenPOWER/POWER9 AI webinar
OpenPOWER/POWER9 AI webinar OpenPOWER/POWER9 AI webinar
OpenPOWER/POWER9 AI webinar
Ganesan Narayanasamy
 
iData Sciences Product Overview
iData Sciences Product OverviewiData Sciences Product Overview
iData Sciences Product Overview
jvsrinivas1
 
Azure Cognitive Services - Custom Vision
Azure Cognitive Services  - Custom VisionAzure Cognitive Services  - Custom Vision
Azure Cognitive Services - Custom Vision
Luis Beltran
 
2024-02-24_Session 1 - PMLE_UPDATED.pptx
2024-02-24_Session 1 - PMLE_UPDATED.pptx2024-02-24_Session 1 - PMLE_UPDATED.pptx
2024-02-24_Session 1 - PMLE_UPDATED.pptx
gdgsurrey
 
Artificial Intelligence with Python | Edureka
Artificial Intelligence with Python | EdurekaArtificial Intelligence with Python | Edureka
Artificial Intelligence with Python | Edureka
Edureka!
 
Microsoft Cognitive Services at a Glance
Microsoft Cognitive Services at a GlanceMicrosoft Cognitive Services at a Glance
Microsoft Cognitive Services at a Glance
Marvin Heng
 
Using Algorithmia to leverage AI and Machine Learning APIs
Using Algorithmia to leverage AI and Machine Learning APIsUsing Algorithmia to leverage AI and Machine Learning APIs
Using Algorithmia to leverage AI and Machine Learning APIs
Rakuten Group, Inc.
 
A guide to Face Detection in Python.pdf
A guide to Face Detection in Python.pdfA guide to Face Detection in Python.pdf
A guide to Face Detection in Python.pdf
3sitservices IT Software Company
 
Ria Sankar on Building AI Products
Ria Sankar on Building AI ProductsRia Sankar on Building AI Products
Ria Sankar on Building AI Products
Ria Sankar
 
Data Workflows for Machine Learning - SF Bay Area ML
Data Workflows for Machine Learning - SF Bay Area MLData Workflows for Machine Learning - SF Bay Area ML
Data Workflows for Machine Learning - SF Bay Area ML
Paco Nathan
 
What are the Unique Challenges and Opportunities in Systems for ML?
What are the Unique Challenges and Opportunities in Systems for ML?What are the Unique Challenges and Opportunities in Systems for ML?
What are the Unique Challenges and Opportunities in Systems for ML?
Matei Zaharia
 
Bridging the Gap: Analyzing Data in and Below the Cloud
Bridging the Gap: Analyzing Data in and Below the CloudBridging the Gap: Analyzing Data in and Below the Cloud
Bridging the Gap: Analyzing Data in and Below the Cloud
Inside Analysis
 
"Machine Learning for .NET Developers", Oleksander Krakovetskyi
"Machine Learning for .NET Developers", Oleksander Krakovetskyi"Machine Learning for .NET Developers", Oleksander Krakovetskyi
"Machine Learning for .NET Developers", Oleksander Krakovetskyi
Fwdays
 
Beautiful Models in PHP
Beautiful Models in PHPBeautiful Models in PHP
Beautiful Models in PHPbrandonsavage
 
Using Data Science to Build an End-to-End Recommendation System
Using Data Science to Build an End-to-End Recommendation SystemUsing Data Science to Build an End-to-End Recommendation System
Using Data Science to Build an End-to-End Recommendation System
VMware Tanzu
 
التقنيات المستخدمة لتطوير المكتبات
التقنيات المستخدمة لتطوير المكتباتالتقنيات المستخدمة لتطوير المكتبات
التقنيات المستخدمة لتطوير المكتبات
Mohammed El Rafie Tarabay
 
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Codemotion
 

Similar to Yurii Pashchenko: Tips and tricks for building your own automated visual data annotation system (20)

From c# Into Machine Learning
From c# Into Machine LearningFrom c# Into Machine Learning
From c# Into Machine Learning
 
AI for Software Engineering
AI for Software EngineeringAI for Software Engineering
AI for Software Engineering
 
Data Workflows for Machine Learning - Seattle DAML
Data Workflows for Machine Learning - Seattle DAMLData Workflows for Machine Learning - Seattle DAML
Data Workflows for Machine Learning - Seattle DAML
 
OpenPOWER/POWER9 AI webinar
OpenPOWER/POWER9 AI webinar OpenPOWER/POWER9 AI webinar
OpenPOWER/POWER9 AI webinar
 
iData Sciences Product Overview
iData Sciences Product OverviewiData Sciences Product Overview
iData Sciences Product Overview
 
Azure Cognitive Services - Custom Vision
Azure Cognitive Services  - Custom VisionAzure Cognitive Services  - Custom Vision
Azure Cognitive Services - Custom Vision
 
2024-02-24_Session 1 - PMLE_UPDATED.pptx
2024-02-24_Session 1 - PMLE_UPDATED.pptx2024-02-24_Session 1 - PMLE_UPDATED.pptx
2024-02-24_Session 1 - PMLE_UPDATED.pptx
 
Artificial Intelligence with Python | Edureka
Artificial Intelligence with Python | EdurekaArtificial Intelligence with Python | Edureka
Artificial Intelligence with Python | Edureka
 
Microsoft Cognitive Services at a Glance
Microsoft Cognitive Services at a GlanceMicrosoft Cognitive Services at a Glance
Microsoft Cognitive Services at a Glance
 
Using Algorithmia to leverage AI and Machine Learning APIs
Using Algorithmia to leverage AI and Machine Learning APIsUsing Algorithmia to leverage AI and Machine Learning APIs
Using Algorithmia to leverage AI and Machine Learning APIs
 
A guide to Face Detection in Python.pdf
A guide to Face Detection in Python.pdfA guide to Face Detection in Python.pdf
A guide to Face Detection in Python.pdf
 
Ria Sankar on Building AI Products
Ria Sankar on Building AI ProductsRia Sankar on Building AI Products
Ria Sankar on Building AI Products
 
Data Workflows for Machine Learning - SF Bay Area ML
Data Workflows for Machine Learning - SF Bay Area MLData Workflows for Machine Learning - SF Bay Area ML
Data Workflows for Machine Learning - SF Bay Area ML
 
What are the Unique Challenges and Opportunities in Systems for ML?
What are the Unique Challenges and Opportunities in Systems for ML?What are the Unique Challenges and Opportunities in Systems for ML?
What are the Unique Challenges and Opportunities in Systems for ML?
 
Bridging the Gap: Analyzing Data in and Below the Cloud
Bridging the Gap: Analyzing Data in and Below the CloudBridging the Gap: Analyzing Data in and Below the Cloud
Bridging the Gap: Analyzing Data in and Below the Cloud
 
"Machine Learning for .NET Developers", Oleksander Krakovetskyi
"Machine Learning for .NET Developers", Oleksander Krakovetskyi"Machine Learning for .NET Developers", Oleksander Krakovetskyi
"Machine Learning for .NET Developers", Oleksander Krakovetskyi
 
Beautiful Models in PHP
Beautiful Models in PHPBeautiful Models in PHP
Beautiful Models in PHP
 
Using Data Science to Build an End-to-End Recommendation System
Using Data Science to Build an End-to-End Recommendation SystemUsing Data Science to Build an End-to-End Recommendation System
Using Data Science to Build an End-to-End Recommendation System
 
التقنيات المستخدمة لتطوير المكتبات
التقنيات المستخدمة لتطوير المكتباتالتقنيات المستخدمة لتطوير المكتبات
التقنيات المستخدمة لتطوير المكتبات
 
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
 

More from Lviv Startup Club

Artem Bykovets: Чому люди не стають раптово кросс-функціональними, хоча в нас...
Artem Bykovets: Чому люди не стають раптово кросс-функціональними, хоча в нас...Artem Bykovets: Чому люди не стають раптово кросс-функціональними, хоча в нас...
Artem Bykovets: Чому люди не стають раптово кросс-функціональними, хоча в нас...
Lviv Startup Club
 
Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...
Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...
Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...
Lviv Startup Club
 
Helen Lubchak: Тренди в управлінні проєктами та miltech (UA)
Helen Lubchak: Тренди в управлінні проєктами та miltech (UA)Helen Lubchak: Тренди в управлінні проєктами та miltech (UA)
Helen Lubchak: Тренди в управлінні проєктами та miltech (UA)
Lviv Startup Club
 
Maksym Vyshnivetskyi: PMO Quality Management (UA)
Maksym Vyshnivetskyi: PMO Quality Management (UA)Maksym Vyshnivetskyi: PMO Quality Management (UA)
Maksym Vyshnivetskyi: PMO Quality Management (UA)
Lviv Startup Club
 
Anatolii Vintsyk: Комунікації в проєкті під час війни (UA)
Anatolii Vintsyk: Комунікації в проєкті під час війни (UA)Anatolii Vintsyk: Комунікації в проєкті під час війни (UA)
Anatolii Vintsyk: Комунікації в проєкті під час війни (UA)
Lviv Startup Club
 
Natalia Renska & Roman Astafiev: Нарциси і психопати в організаціях. Як це вп...
Natalia Renska & Roman Astafiev: Нарциси і психопати в організаціях. Як це вп...Natalia Renska & Roman Astafiev: Нарциси і психопати в організаціях. Як це вп...
Natalia Renska & Roman Astafiev: Нарциси і психопати в організаціях. Як це вп...
Lviv Startup Club
 
Diana Natkhir: Інструменти Change management для роботи з клієнтами в продукт...
Diana Natkhir: Інструменти Change management для роботи з клієнтами в продукт...Diana Natkhir: Інструменти Change management для роботи з клієнтами в продукт...
Diana Natkhir: Інструменти Change management для роботи з клієнтами в продукт...
Lviv Startup Club
 
Khristina Pototska: Steering the Ship: Product Management in Startups vs. Glo...
Khristina Pototska: Steering the Ship: Product Management in Startups vs. Glo...Khristina Pototska: Steering the Ship: Product Management in Startups vs. Glo...
Khristina Pototska: Steering the Ship: Product Management in Startups vs. Glo...
Lviv Startup Club
 
Oleksandr Buratynskyi: Як Agile Coach мікроменеджером став 🙃 (UA)
Oleksandr Buratynskyi: Як Agile Coach мікроменеджером став 🙃 (UA)Oleksandr Buratynskyi: Як Agile Coach мікроменеджером став 🙃 (UA)
Oleksandr Buratynskyi: Як Agile Coach мікроменеджером став 🙃 (UA)
Lviv Startup Club
 
Igor Protsenko: Difference between outsourcing and product companies for prod...
Igor Protsenko: Difference between outsourcing and product companies for prod...Igor Protsenko: Difference between outsourcing and product companies for prod...
Igor Protsenko: Difference between outsourcing and product companies for prod...
Lviv Startup Club
 
Kseniya Leshchenko: Shared development support service model as the way to ma...
Kseniya Leshchenko: Shared development support service model as the way to ma...Kseniya Leshchenko: Shared development support service model as the way to ma...
Kseniya Leshchenko: Shared development support service model as the way to ma...
Lviv Startup Club
 
Valeriy Kozlov: Taming the Startup Chaos: GTD for Founders & Small Teams (UA)
Valeriy Kozlov: Taming the Startup Chaos: GTD for Founders & Small Teams (UA)Valeriy Kozlov: Taming the Startup Chaos: GTD for Founders & Small Teams (UA)
Valeriy Kozlov: Taming the Startup Chaos: GTD for Founders & Small Teams (UA)
Lviv Startup Club
 
Anna Kompanets: Проблеми впровадження проєктів, про які б ви ніколи не подума...
Anna Kompanets: Проблеми впровадження проєктів, про які б ви ніколи не подума...Anna Kompanets: Проблеми впровадження проєктів, про які б ви ніколи не подума...
Anna Kompanets: Проблеми впровадження проєктів, про які б ви ніколи не подума...
Lviv Startup Club
 
Viktoriia Honcharova: PMI: нова стратегія розвитку управління проєктами (UA)
Viktoriia Honcharova: PMI: нова стратегія розвитку управління проєктами (UA)Viktoriia Honcharova: PMI: нова стратегія розвитку управління проєктами (UA)
Viktoriia Honcharova: PMI: нова стратегія розвитку управління проєктами (UA)
Lviv Startup Club
 
Andrii Mandrika: Як системно допомагати ЗСУ, використовуючи продуктовий підхі...
Andrii Mandrika: Як системно допомагати ЗСУ, використовуючи продуктовий підхі...Andrii Mandrika: Як системно допомагати ЗСУ, використовуючи продуктовий підхі...
Andrii Mandrika: Як системно допомагати ЗСУ, використовуючи продуктовий підхі...
Lviv Startup Club
 
Michael Vidyakin: From Vision to Victory: Mastering the Project-Strategy Conn...
Michael Vidyakin: From Vision to Victory: Mastering the Project-Strategy Conn...Michael Vidyakin: From Vision to Victory: Mastering the Project-Strategy Conn...
Michael Vidyakin: From Vision to Victory: Mastering the Project-Strategy Conn...
Lviv Startup Club
 
Kateryna Kubasova: Абстрактне Оксфордське лідерство конкретному українському ...
Kateryna Kubasova: Абстрактне Оксфордське лідерство конкретному українському ...Kateryna Kubasova: Абстрактне Оксфордське лідерство конкретному українському ...
Kateryna Kubasova: Абстрактне Оксфордське лідерство конкретному українському ...
Lviv Startup Club
 
Andrii Salii: Навіщо публічному сектору NPS: будуємо довіру через відкритість...
Andrii Salii: Навіщо публічному сектору NPS: будуємо довіру через відкритість...Andrii Salii: Навіщо публічному сектору NPS: будуємо довіру через відкритість...
Andrii Salii: Навіщо публічному сектору NPS: будуємо довіру через відкритість...
Lviv Startup Club
 
Anton Hlazkov: Впровадження змін – це процес чи проєкт? Чому важливо розуміти...
Anton Hlazkov: Впровадження змін – це процес чи проєкт? Чому важливо розуміти...Anton Hlazkov: Впровадження змін – це процес чи проєкт? Чому важливо розуміти...
Anton Hlazkov: Впровадження змін – це процес чи проєкт? Чому важливо розуміти...
Lviv Startup Club
 
Yana Bort: Ритм організації. Чи можливо синхронізувати великий ентерпрайз за ...
Yana Bort: Ритм організації. Чи можливо синхронізувати великий ентерпрайз за ...Yana Bort: Ритм організації. Чи можливо синхронізувати великий ентерпрайз за ...
Yana Bort: Ритм організації. Чи можливо синхронізувати великий ентерпрайз за ...
Lviv Startup Club
 

More from Lviv Startup Club (20)

Artem Bykovets: Чому люди не стають раптово кросс-функціональними, хоча в нас...
Artem Bykovets: Чому люди не стають раптово кросс-функціональними, хоча в нас...Artem Bykovets: Чому люди не стають раптово кросс-функціональними, хоча в нас...
Artem Bykovets: Чому люди не стають раптово кросс-функціональними, хоча в нас...
 
Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...
Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...
Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...
 
Helen Lubchak: Тренди в управлінні проєктами та miltech (UA)
Helen Lubchak: Тренди в управлінні проєктами та miltech (UA)Helen Lubchak: Тренди в управлінні проєктами та miltech (UA)
Helen Lubchak: Тренди в управлінні проєктами та miltech (UA)
 
Maksym Vyshnivetskyi: PMO Quality Management (UA)
Maksym Vyshnivetskyi: PMO Quality Management (UA)Maksym Vyshnivetskyi: PMO Quality Management (UA)
Maksym Vyshnivetskyi: PMO Quality Management (UA)
 
Anatolii Vintsyk: Комунікації в проєкті під час війни (UA)
Anatolii Vintsyk: Комунікації в проєкті під час війни (UA)Anatolii Vintsyk: Комунікації в проєкті під час війни (UA)
Anatolii Vintsyk: Комунікації в проєкті під час війни (UA)
 
Natalia Renska & Roman Astafiev: Нарциси і психопати в організаціях. Як це вп...
Natalia Renska & Roman Astafiev: Нарциси і психопати в організаціях. Як це вп...Natalia Renska & Roman Astafiev: Нарциси і психопати в організаціях. Як це вп...
Natalia Renska & Roman Astafiev: Нарциси і психопати в організаціях. Як це вп...
 
Diana Natkhir: Інструменти Change management для роботи з клієнтами в продукт...
Diana Natkhir: Інструменти Change management для роботи з клієнтами в продукт...Diana Natkhir: Інструменти Change management для роботи з клієнтами в продукт...
Diana Natkhir: Інструменти Change management для роботи з клієнтами в продукт...
 
Khristina Pototska: Steering the Ship: Product Management in Startups vs. Glo...
Khristina Pototska: Steering the Ship: Product Management in Startups vs. Glo...Khristina Pototska: Steering the Ship: Product Management in Startups vs. Glo...
Khristina Pototska: Steering the Ship: Product Management in Startups vs. Glo...
 
Oleksandr Buratynskyi: Як Agile Coach мікроменеджером став 🙃 (UA)
Oleksandr Buratynskyi: Як Agile Coach мікроменеджером став 🙃 (UA)Oleksandr Buratynskyi: Як Agile Coach мікроменеджером став 🙃 (UA)
Oleksandr Buratynskyi: Як Agile Coach мікроменеджером став 🙃 (UA)
 
Igor Protsenko: Difference between outsourcing and product companies for prod...
Igor Protsenko: Difference between outsourcing and product companies for prod...Igor Protsenko: Difference between outsourcing and product companies for prod...
Igor Protsenko: Difference between outsourcing and product companies for prod...
 
Kseniya Leshchenko: Shared development support service model as the way to ma...
Kseniya Leshchenko: Shared development support service model as the way to ma...Kseniya Leshchenko: Shared development support service model as the way to ma...
Kseniya Leshchenko: Shared development support service model as the way to ma...
 
Valeriy Kozlov: Taming the Startup Chaos: GTD for Founders & Small Teams (UA)
Valeriy Kozlov: Taming the Startup Chaos: GTD for Founders & Small Teams (UA)Valeriy Kozlov: Taming the Startup Chaos: GTD for Founders & Small Teams (UA)
Valeriy Kozlov: Taming the Startup Chaos: GTD for Founders & Small Teams (UA)
 
Anna Kompanets: Проблеми впровадження проєктів, про які б ви ніколи не подума...
Anna Kompanets: Проблеми впровадження проєктів, про які б ви ніколи не подума...Anna Kompanets: Проблеми впровадження проєктів, про які б ви ніколи не подума...
Anna Kompanets: Проблеми впровадження проєктів, про які б ви ніколи не подума...
 
Viktoriia Honcharova: PMI: нова стратегія розвитку управління проєктами (UA)
Viktoriia Honcharova: PMI: нова стратегія розвитку управління проєктами (UA)Viktoriia Honcharova: PMI: нова стратегія розвитку управління проєктами (UA)
Viktoriia Honcharova: PMI: нова стратегія розвитку управління проєктами (UA)
 
Andrii Mandrika: Як системно допомагати ЗСУ, використовуючи продуктовий підхі...
Andrii Mandrika: Як системно допомагати ЗСУ, використовуючи продуктовий підхі...Andrii Mandrika: Як системно допомагати ЗСУ, використовуючи продуктовий підхі...
Andrii Mandrika: Як системно допомагати ЗСУ, використовуючи продуктовий підхі...
 
Michael Vidyakin: From Vision to Victory: Mastering the Project-Strategy Conn...
Michael Vidyakin: From Vision to Victory: Mastering the Project-Strategy Conn...Michael Vidyakin: From Vision to Victory: Mastering the Project-Strategy Conn...
Michael Vidyakin: From Vision to Victory: Mastering the Project-Strategy Conn...
 
Kateryna Kubasova: Абстрактне Оксфордське лідерство конкретному українському ...
Kateryna Kubasova: Абстрактне Оксфордське лідерство конкретному українському ...Kateryna Kubasova: Абстрактне Оксфордське лідерство конкретному українському ...
Kateryna Kubasova: Абстрактне Оксфордське лідерство конкретному українському ...
 
Andrii Salii: Навіщо публічному сектору NPS: будуємо довіру через відкритість...
Andrii Salii: Навіщо публічному сектору NPS: будуємо довіру через відкритість...Andrii Salii: Навіщо публічному сектору NPS: будуємо довіру через відкритість...
Andrii Salii: Навіщо публічному сектору NPS: будуємо довіру через відкритість...
 
Anton Hlazkov: Впровадження змін – це процес чи проєкт? Чому важливо розуміти...
Anton Hlazkov: Впровадження змін – це процес чи проєкт? Чому важливо розуміти...Anton Hlazkov: Впровадження змін – це процес чи проєкт? Чому важливо розуміти...
Anton Hlazkov: Впровадження змін – це процес чи проєкт? Чому важливо розуміти...
 
Yana Bort: Ритм організації. Чи можливо синхронізувати великий ентерпрайз за ...
Yana Bort: Ритм організації. Чи можливо синхронізувати великий ентерпрайз за ...Yana Bort: Ритм організації. Чи можливо синхронізувати великий ентерпрайз за ...
Yana Bort: Ритм організації. Чи можливо синхронізувати великий ентерпрайз за ...
 

Recently uploaded

Brand Analysis for an artist named Struan
Brand Analysis for an artist named StruanBrand Analysis for an artist named Struan
Brand Analysis for an artist named Struan
sarahvanessa51503
 
The Parable of the Pipeline a book every new businessman or business student ...
The Parable of the Pipeline a book every new businessman or business student ...The Parable of the Pipeline a book every new businessman or business student ...
The Parable of the Pipeline a book every new businessman or business student ...
awaisafdar
 
Discover the innovative and creative projects that highlight my journey throu...
Discover the innovative and creative projects that highlight my journey throu...Discover the innovative and creative projects that highlight my journey throu...
Discover the innovative and creative projects that highlight my journey throu...
dylandmeas
 
What are the main advantages of using HR recruiter services.pdf
What are the main advantages of using HR recruiter services.pdfWhat are the main advantages of using HR recruiter services.pdf
What are the main advantages of using HR recruiter services.pdf
HumanResourceDimensi1
 
3.0 Project 2_ Developing My Brand Identity Kit.pptx
3.0 Project 2_ Developing My Brand Identity Kit.pptx3.0 Project 2_ Developing My Brand Identity Kit.pptx
3.0 Project 2_ Developing My Brand Identity Kit.pptx
tanyjahb
 
RMD24 | Retail media: hoe zet je dit in als je geen AH of Unilever bent? Heid...
RMD24 | Retail media: hoe zet je dit in als je geen AH of Unilever bent? Heid...RMD24 | Retail media: hoe zet je dit in als je geen AH of Unilever bent? Heid...
RMD24 | Retail media: hoe zet je dit in als je geen AH of Unilever bent? Heid...
BBPMedia1
 
The-McKinsey-7S-Framework. strategic management
The-McKinsey-7S-Framework. strategic managementThe-McKinsey-7S-Framework. strategic management
The-McKinsey-7S-Framework. strategic management
Bojamma2
 
CADAVER AS OUR FIRST TEACHER anatomt in your.pptx
CADAVER AS OUR FIRST TEACHER anatomt in your.pptxCADAVER AS OUR FIRST TEACHER anatomt in your.pptx
CADAVER AS OUR FIRST TEACHER anatomt in your.pptx
fakeloginn69
 
Meas_Dylan_DMBS_PB1_2024-05XX_Revised.pdf
Meas_Dylan_DMBS_PB1_2024-05XX_Revised.pdfMeas_Dylan_DMBS_PB1_2024-05XX_Revised.pdf
Meas_Dylan_DMBS_PB1_2024-05XX_Revised.pdf
dylandmeas
 
BeMetals Presentation_May_22_2024 .pdf
BeMetals Presentation_May_22_2024   .pdfBeMetals Presentation_May_22_2024   .pdf
BeMetals Presentation_May_22_2024 .pdf
DerekIwanaka1
 
Tata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s Dholera
Tata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s DholeraTata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s Dholera
Tata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s Dholera
Avirahi City Dholera
 
What is the TDS Return Filing Due Date for FY 2024-25.pdf
What is the TDS Return Filing Due Date for FY 2024-25.pdfWhat is the TDS Return Filing Due Date for FY 2024-25.pdf
What is the TDS Return Filing Due Date for FY 2024-25.pdf
seoforlegalpillers
 
Introduction to Amazon company 111111111111
Introduction to Amazon company 111111111111Introduction to Amazon company 111111111111
Introduction to Amazon company 111111111111
zoyaansari11365
 
The Influence of Marketing Strategy and Market Competition on Business Perfor...
The Influence of Marketing Strategy and Market Competition on Business Perfor...The Influence of Marketing Strategy and Market Competition on Business Perfor...
The Influence of Marketing Strategy and Market Competition on Business Perfor...
Adam Smith
 
Business Valuation Principles for Entrepreneurs
Business Valuation Principles for EntrepreneursBusiness Valuation Principles for Entrepreneurs
Business Valuation Principles for Entrepreneurs
Ben Wann
 
Sustainability: Balancing the Environment, Equity & Economy
Sustainability: Balancing the Environment, Equity & EconomySustainability: Balancing the Environment, Equity & Economy
Sustainability: Balancing the Environment, Equity & Economy
Operational Excellence Consulting
 
anas about venice for grade 6f about venice
anas about venice for grade 6f about veniceanas about venice for grade 6f about venice
anas about venice for grade 6f about venice
anasabutalha2013
 
Premium MEAN Stack Development Solutions for Modern Businesses
Premium MEAN Stack Development Solutions for Modern BusinessesPremium MEAN Stack Development Solutions for Modern Businesses
Premium MEAN Stack Development Solutions for Modern Businesses
SynapseIndia
 
Digital Transformation and IT Strategy Toolkit and Templates
Digital Transformation and IT Strategy Toolkit and TemplatesDigital Transformation and IT Strategy Toolkit and Templates
Digital Transformation and IT Strategy Toolkit and Templates
Aurelien Domont, MBA
 
Unveiling the Secrets How Does Generative AI Work.pdf
Unveiling the Secrets How Does Generative AI Work.pdfUnveiling the Secrets How Does Generative AI Work.pdf
Unveiling the Secrets How Does Generative AI Work.pdf
Sam H
 

Recently uploaded (20)

Brand Analysis for an artist named Struan
Brand Analysis for an artist named StruanBrand Analysis for an artist named Struan
Brand Analysis for an artist named Struan
 
The Parable of the Pipeline a book every new businessman or business student ...
The Parable of the Pipeline a book every new businessman or business student ...The Parable of the Pipeline a book every new businessman or business student ...
The Parable of the Pipeline a book every new businessman or business student ...
 
Discover the innovative and creative projects that highlight my journey throu...
Discover the innovative and creative projects that highlight my journey throu...Discover the innovative and creative projects that highlight my journey throu...
Discover the innovative and creative projects that highlight my journey throu...
 
What are the main advantages of using HR recruiter services.pdf
What are the main advantages of using HR recruiter services.pdfWhat are the main advantages of using HR recruiter services.pdf
What are the main advantages of using HR recruiter services.pdf
 
3.0 Project 2_ Developing My Brand Identity Kit.pptx
3.0 Project 2_ Developing My Brand Identity Kit.pptx3.0 Project 2_ Developing My Brand Identity Kit.pptx
3.0 Project 2_ Developing My Brand Identity Kit.pptx
 
RMD24 | Retail media: hoe zet je dit in als je geen AH of Unilever bent? Heid...
RMD24 | Retail media: hoe zet je dit in als je geen AH of Unilever bent? Heid...RMD24 | Retail media: hoe zet je dit in als je geen AH of Unilever bent? Heid...
RMD24 | Retail media: hoe zet je dit in als je geen AH of Unilever bent? Heid...
 
The-McKinsey-7S-Framework. strategic management
The-McKinsey-7S-Framework. strategic managementThe-McKinsey-7S-Framework. strategic management
The-McKinsey-7S-Framework. strategic management
 
CADAVER AS OUR FIRST TEACHER anatomt in your.pptx
CADAVER AS OUR FIRST TEACHER anatomt in your.pptxCADAVER AS OUR FIRST TEACHER anatomt in your.pptx
CADAVER AS OUR FIRST TEACHER anatomt in your.pptx
 
Meas_Dylan_DMBS_PB1_2024-05XX_Revised.pdf
Meas_Dylan_DMBS_PB1_2024-05XX_Revised.pdfMeas_Dylan_DMBS_PB1_2024-05XX_Revised.pdf
Meas_Dylan_DMBS_PB1_2024-05XX_Revised.pdf
 
BeMetals Presentation_May_22_2024 .pdf
BeMetals Presentation_May_22_2024   .pdfBeMetals Presentation_May_22_2024   .pdf
BeMetals Presentation_May_22_2024 .pdf
 
Tata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s Dholera
Tata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s DholeraTata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s Dholera
Tata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s Dholera
 
What is the TDS Return Filing Due Date for FY 2024-25.pdf
What is the TDS Return Filing Due Date for FY 2024-25.pdfWhat is the TDS Return Filing Due Date for FY 2024-25.pdf
What is the TDS Return Filing Due Date for FY 2024-25.pdf
 
Introduction to Amazon company 111111111111
Introduction to Amazon company 111111111111Introduction to Amazon company 111111111111
Introduction to Amazon company 111111111111
 
The Influence of Marketing Strategy and Market Competition on Business Perfor...
The Influence of Marketing Strategy and Market Competition on Business Perfor...The Influence of Marketing Strategy and Market Competition on Business Perfor...
The Influence of Marketing Strategy and Market Competition on Business Perfor...
 
Business Valuation Principles for Entrepreneurs
Business Valuation Principles for EntrepreneursBusiness Valuation Principles for Entrepreneurs
Business Valuation Principles for Entrepreneurs
 
Sustainability: Balancing the Environment, Equity & Economy
Sustainability: Balancing the Environment, Equity & EconomySustainability: Balancing the Environment, Equity & Economy
Sustainability: Balancing the Environment, Equity & Economy
 
anas about venice for grade 6f about venice
anas about venice for grade 6f about veniceanas about venice for grade 6f about venice
anas about venice for grade 6f about venice
 
Premium MEAN Stack Development Solutions for Modern Businesses
Premium MEAN Stack Development Solutions for Modern BusinessesPremium MEAN Stack Development Solutions for Modern Businesses
Premium MEAN Stack Development Solutions for Modern Businesses
 
Digital Transformation and IT Strategy Toolkit and Templates
Digital Transformation and IT Strategy Toolkit and TemplatesDigital Transformation and IT Strategy Toolkit and Templates
Digital Transformation and IT Strategy Toolkit and Templates
 
Unveiling the Secrets How Does Generative AI Work.pdf
Unveiling the Secrets How Does Generative AI Work.pdfUnveiling the Secrets How Does Generative AI Work.pdf
Unveiling the Secrets How Does Generative AI Work.pdf
 

Yurii Pashchenko: Tips and tricks for building your own automated visual data annotation system

  • 1. Tips and tricks for building your own automated visual data annotation systems Sr ML Engineer at Depositphotos AI&BigData Online Day 2022
  • 2. About me ❏ Yurii Pashchenko ❏ Sr Machine Learning Engineer at Depositphotos ❏ Over 9 years of research and commercial experience in applying Deep Learning models ❏ Object Detection and Face Recognition Specialist
  • 3. Tips and tricks for building your own automated visual data annotation systems ❏ What is data annotation ❏ Types of visual data annotation ❏ Why data annotation is so important ❏ Challenges in the Image Annotation process ❏ Computer Vision Open Source libraries ❏ Annotation of novel classes ❏ Relevant Sample Search ❏ Zero-Shot Classification ❏ Few-Shot Semantic Segmentation ❏ Open-Vocabulary Object Detection
  • 4. What is data annotation “Computers can't process visual information the way human brains do: A computer needs to be told what it's interpreting and provided context in order to make decisions. Data annotation makes those connections. It's the human-led task of labeling content such as text, audio, images and video so it can be recognized by machine learning models and used to make predictions.” What is data annotation and why does it matter?
  • 5.
  • 6. Why it so important ● Data is the backbone of the customer experience. How well you know your clients directly impacts the quality of their experiences. ● Noticeable correlation between correctly annotated data and the success of the project ● As much as image annotated data is used to train the machine learning model, the accuracy will be higher. ● If you are working on an unsupervised machine learning project, sooner or later, you might need to have data annotation work done if you want to reach better performance of the algorithms.
  • 7. Challenges in the Image Annotation Process Balancing costs with accuracy levels: There are two primary data annotation methods—human annotation and automated annotation. Human annotation typically takes longer and costs more than automated annotation, and also requires training for annotators, but achieves more accurate results. In comparison, automated annotation is more cost-effective but it can be difficult to determine the accuracy level of the results. Guaranteeing consistent data: Machine learning models need a good quality of consistent data to make accurate predictions. However, data labelers may interpret subjective data differently due to their beliefs, culture, and personal biases. If data is labeled inconsistently, the results of a machine learning model will also be skewed. Choosing a suitable annotation tool: There are many image annotation platforms and tools, each providing different capabilities for different types of annotations. The variety of offerings can make it difficult to choose the most suitable tools for each project. It can also be challenging to choose the right tool to match the skillsets of your workforce. Image Annotation for Computer Vision: A Practical Guide
  • 8. Available annotation tools 1. V7 2. Labelbox 3. Scale AI 4. SuperAnnotate 5. Dataloop 6. Playment 7. Supervise.ly 8. Hive Data 9. CVAT 10. LabelMe 11. LabeIimg 12. VoTT 13. Img Lab 13 Best Image Annotation Tools of 2022
  • 9. Tips and tricks for building your own automated visual data annotation systems ❏ What is data annotation ❏ Types of visual data annotation ❏ Why data annotation is so important ❏ Challenges in the Image Annotation process ❏ Computer Vision Open Source libraries ❏ Annotation of novel classes ❏ Relevant Sample Search ❏ Zero-Shot Classification ❏ Object Detection/Segmentation ❏ Few-Shot Semantic Segmentation ❏ Open-Vocabulary Object Detection
  • 10. Detectron2 Detectron2 ● Facebook AI ● Various tasks ● Unified configs ● Inference speed (fast)
  • 11. OpenMMLab ● Modular Design ● Support of multiple frameworks out of the box ● High efficiency ● State of the art OpenMMLab
  • 12. Tips and tricks for building your own automated visual data annotation systems ❏ What is data annotation ❏ Types of visual data annotation ❏ Why data annotation is so important ❏ Challenges in the Image Annotation process ❏ Computer Vision Open Source libraries ❏ Annotation of novel classes ❏ Relevant Sample Search ❏ Zero-Shot Classification ❏ Object Detection/Segmentation ❏ Few-Shot Semantic Segmentation ❏ Open-Vocabulary Object Detection
  • 13. Relevant image search Image search engine using Deep Learning Model
  • 14. Relevant image search Recipe: 1. Preparation a. Convert images to 224x224x3 b. Extract features by VGG16 model of size 4096 c. Store embeddings 2. Comparison a. Extract features for reference image b. Compute distance (cosine) between input feature and all embeddings in dataset c. Sort distances in ascending order d. Show first k-images Image search engine using Deep Learning Model Limitations: ● only for similarity search ● features are not representative on real-world samples ● Applicable for datasets 1-10K in terms of speed
  • 15. Tips and tricks for building your own automated visual data annotation systems ❏ What is data annotation ❏ Types of visual data annotation ❏ Challenges in the Image Annotation process ❏ Why data annotation is so important ❏ Computer Vision Open Source libraries ❏ Annotation of novel classes ❏ Relevant Sample Search ❏ Zero-Shot Classification ❏ Object Detection/Segmentation ❏ Few-Shot Semantic Segmentation ❏ Open-Vocabulary Object Detection
  • 16. CLIP: Contrastive Language-Image Pre-training Learning Transferable Visual Models From Natural Language Supervision ● 400 million (image, text) pairs collected from Internet. ● Trained modifications of ResNet-50 and ViT-B ● Batch size 32 768 for 32 epochs ● The largest ResNet model, RN50x64, took 18 days to train on 592 V100 GPUs while the largest Vision Transformer took 12 days on 256 V100 GPUs
  • 17. CLIP for Zero-Shot Classification Learning Transferable Visual Models From Natural Language Supervision Ensembling around 80 prompts improve ImageNet accuracy by almost 5%
  • 18. Facebook AI Similarity Search (FAISS) Faiss: A library for efficient similarity search
  • 19. CLIP-based Image Search Text-to-Image Unsplash Image Search "Two dogs playing in the snow" “The world love written on the wall” “The feeling when your program finally works”
  • 20. CLIP-based for Image Search Image+Text-to-Image Unsplash Image Search + “cars”
  • 21. Tips and tricks for building your own automated visual data annotation systems ❏ What is data annotation ❏ Types of visual data annotation ❏ Challenges in the Image Annotation process ❏ Why data annotation is so important ❏ Computer Vision Open Source libraries ❏ Annotation of novel classes ❏ Relevant Sample Search ❏ Zero-Shot Classification ❏ Object Detection/Segmentation ❏ Few-Shot Semantic Segmentation ❏ Open-Vocabulary Object Detection
  • 22. You can’t just make an Object Detector from a Classifier … without fine-tuning
  • 23. Assembling Object Detector with CLIP Rich feature hierarchies for accurate object detection and semantic segmentation CLIP Text Encoder person
  • 24. Region proposals alternatives Salient Object Detection Techniques in Computer Vision—A Survey Salient object detection (SOD) is an important computer vision task aimed at precise detection and segmentation of visually distinctive image regions from the perspective of the human visual system
  • 25. Region proposals alternatives Open-World Entity Segmentation Entity Segmentation is a segmentation task with the aim to segment everything in an image into semantically-meaningful regions without considering any category labels.
  • 26. Tips and tricks for building your own automated visual data annotation systems ❏ What is data annotation ❏ Types of visual data annotation ❏ Challenges in the Image Annotation process ❏ Why data annotation is so important ❏ Computer Vision Open Source libraries ❏ Annotation of novel classes ❏ Relevant Sample Search ❏ Zero-Shot Classification ❏ Object Detection/Segmentation ❏ Few-Shot Semantic Segmentation ❏ Open-Vocabulary Object Detection
  • 27. Few-Shot Semantic Segmentation MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation
  • 28. Few-Shot Semantic Segmentation MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation
  • 29. Tips and tricks for building your own automated visual data annotation systems ❏ What is data annotation ❏ Types of visual data annotation ❏ Challenges in the Image Annotation process ❏ Why data annotation is so important ❏ Computer Vision Open Source libraries ❏ Annotation of novel classes ❏ Relevant Sample Search ❏ Zero-Shot Classification ❏ Object Detection/Segmentation ❏ Few-Shot Semantic Segmentation ❏ Open-Vocabulary Object Detection
  • 30. Open Vocabulary Object Detection https://paperswithcode.com/task/open-vocabulary-object-detection/latest Open-vocabulary detection (OVD) aims to generalize beyond the limited number of base classes labeled during the training phase. The goal is to detect novel classes defined by an unbounded (open) vocabulary at inference
  • 31. Vision and Language knowledge Distillation Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
  • 32. VILD generalization ability Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
  • 33. VILD visualizations Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
  • 34. VILD visualizations Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
  • 35. Is it worth it?
  • 36. Thank you for your attention! Yurii Pashchenko AI&BigData Online Day 2022 Yurii Pashchenko Sr ML Engineer at Depositphotos yurii_pas george.pashchenko@gmail.com