The document summarizes research on visualizing features used in object detection models. It presents four methods - ELDA, Ridge, Direct, and Paired Dictionary learning - for inverting high-dimensional feature vectors like HOG back to the input image domain. Evaluation shows Paired Dictionary learning produces the most visually recognizable inversions. It also describes using a technique called deconvnet to visualize features at different layers of a convnet and understand what patterns activate certain features.
Variational Autoencoded Regression of Visual Data with Generative Adversarial...NAVER Engineering
발표자: 유영준 (서울대 박사 후 연구원)
발표일: 2017.8.
Postdoctoral Research Associate: Graduate School of Convergence Science and Technology, Seoul National University. March, 2017
See more info at https://sites.google.com/view/yjyoo3312/
개요:
Presents a new visual image generation method using regression combined with recent deep generative models: VAE, GAN.
This is talk slide at Nagoya Univ. on Dec., 08, 2014. This slides includes some history of neural networks, percetpron, error backpropagation, neocognitron, and convolution net. Also I talk a few topics about sparse coding in the deep architeture
Variational Autoencoded Regression of Visual Data with Generative Adversarial...NAVER Engineering
발표자: 유영준 (서울대 박사 후 연구원)
발표일: 2017.8.
Postdoctoral Research Associate: Graduate School of Convergence Science and Technology, Seoul National University. March, 2017
See more info at https://sites.google.com/view/yjyoo3312/
개요:
Presents a new visual image generation method using regression combined with recent deep generative models: VAE, GAN.
This is talk slide at Nagoya Univ. on Dec., 08, 2014. This slides includes some history of neural networks, percetpron, error backpropagation, neocognitron, and convolution net. Also I talk a few topics about sparse coding in the deep architeture
OpenGL Fixed Function to Shaders - Porting a fixed function application to “m...ICS
Watch the video here: http://bit.ly/1TA24fU
OpenGL Fixed Function to Shaders - Porting a fixed function application to “modern” OpenGL - Webinar Mar 2016
“CariGANs" are the first Generative Adversarial Network (GAN) for unpaired photo-to-caricature translation. In simple terms, this means enabling a machine to learn to create a caricature from a real image without human intervention. Head to https://www.razorthink.com/ to learn more.
OpenGL Fixed Function to Shaders - Porting a fixed function application to “m...ICS
Watch the video here: http://bit.ly/1TA24fU
OpenGL Fixed Function to Shaders - Porting a fixed function application to “modern” OpenGL - Webinar Mar 2016
“CariGANs" are the first Generative Adversarial Network (GAN) for unpaired photo-to-caricature translation. In simple terms, this means enabling a machine to learn to create a caricature from a real image without human intervention. Head to https://www.razorthink.com/ to learn more.
Unsupervised learning representation with Deep Convolutional Generative Adversarial Network, Paper by Alec Radford, Luke Metz, and Soumith Chintala
(indico Research, Facebook AI Research).
Getting more out of Matplotlib with GRJosef Heinen
Matplotlib is the most popular graphics library for Python. It is the workhorse plotting utility of the scientific Python world. However, depending on the field of application, the software may be reaching its limits. This is the point where the GR framework will help. GR can be used as a backend for Matplotlib applications and significantly improve the performance and expand their capabilities.
A simple framework for contrastive learning of visual representationsDevansh16
Link: https://machine-learning-made-simple.medium.com/learnings-from-simclr-a-framework-contrastive-learning-for-visual-representations-6c145a5d8e99
If you'd like to discuss something, text me on LinkedIn, IG, or Twitter. To support me, please use my referral link to Robinhood. It's completely free, and we both get a free stock. Not using it is literally losing out on free money.
Check out my other articles on Medium. : https://rb.gy/zn1aiu
My YouTube: https://rb.gy/88iwdd
Reach out to me on LinkedIn. Let's connect: https://rb.gy/m5ok2y
My Instagram: https://rb.gy/gmvuy9
My Twitter: https://twitter.com/Machine01776819
My Substack: https://devanshacc.substack.com/
Live conversations at twitch here: https://rb.gy/zlhk9y
Get a free stock on Robinhood: https://join.robinhood.com/fnud75
This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank. In order to understand what enables the contrastive prediction tasks to learn useful representations, we systematically study the major components of our framework. We show that (1) composition of data augmentations plays a critical role in defining effective predictive tasks, (2) introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and (3) contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning. By combining these findings, we are able to considerably outperform previous methods for self-supervised and semi-supervised learning on ImageNet. A linear classifier trained on self-supervised representations learned by SimCLR achieves 76.5% top-1 accuracy, which is a 7% relative improvement over previous state-of-the-art, matching the performance of a supervised ResNet-50. When fine-tuned on only 1% of the labels, we achieve 85.8% top-5 accuracy, outperforming AlexNet with 100X fewer labels.
Comments: ICML'2020. Code and pretrained models at this https URL
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)
Cite as: arXiv:2002.05709 [cs.LG]
(or arXiv:2002.05709v3 [cs.LG] for this version)
Submission history
From: Ting Chen [view email]
[v1] Thu, 13 Feb 2020 18:50:45 UTC (5,093 KB)
[v2] Mon, 30 Mar 2020 15:32:51 UTC (5,047 KB)
[v3] Wed, 1 Jul 2020 00:09:08 UTC (5,829 KB)
From Hello World to the Interactive Web with Three.js: Workshop at FutureJS 2014Verold
The first workshop at the first ever FutureJS conference in Barcelona. From Three.js Hello World to building your first interactive 3D app, to connecting your web app with the Internet of Things.
Lab Practices and Works Documentation / Report on Computer GraphicsRup Chowdhury
This is a report that I have prepared during my Computer Graphics Lab course. This contains the theoretical information that we learned in our introduction class. It also contains information on different computer graphics tools and software. It contains codes to create different and also the procedure.
1. Information on GLUT
2. Flag drawing with GLUT
3. DDA Algorithm
4. Midpoint Line Drawing Algorithm
5. Tansformation
One-Sample Face Recognition Using HMM Model of Fiducial AreasCSCJournals
In most real world applications, multiple image samples of individuals are not easy to collate for direct implementation of recognition or verification systems. Therefore there is a need to perform these tasks even if only one training sample per person is available. This paper describes an effective algorithm for recognition and verification with one sample image per class. It uses two dimensional discrete wavelet transform (2D DWT) to extract features from images and hidden Markov model (HMM) was used for training, recognition and classification. It was tested with a subset of the AT&T database and up to 90% correct classification (Hit) and false acceptance rate (FAR) of 0.02% was achieved.
Forklift Classes Overview by Intella PartsIntella Parts
Discover the different forklift classes and their specific applications. Learn how to choose the right forklift for your needs to ensure safety, efficiency, and compliance in your operations.
For more technical information, visit our website https://intellaparts.com
Student information management system project report ii.pdfKamal Acharya
Our project explains about the student management. This project mainly explains the various actions related to student details. This project shows some ease in adding, editing and deleting the student details. It also provides a less time consuming process for viewing, adding, editing and deleting the marks of the students.
Welcome to WIPAC Monthly the magazine brought to you by the LinkedIn Group Water Industry Process Automation & Control.
In this month's edition, along with this month's industry news to celebrate the 13 years since the group was created we have articles including
A case study of the used of Advanced Process Control at the Wastewater Treatment works at Lleida in Spain
A look back on an article on smart wastewater networks in order to see how the industry has measured up in the interim around the adoption of Digital Transformation in the Water Industry.
Using recycled concrete aggregates (RCA) for pavements is crucial to achieving sustainability. Implementing RCA for new pavement can minimize carbon footprint, conserve natural resources, reduce harmful emissions, and lower life cycle costs. Compared to natural aggregate (NA), RCA pavement has fewer comprehensive studies and sustainability assessments.
NO1 Uk best vashikaran specialist in delhi vashikaran baba near me online vas...Amil Baba Dawood bangali
Contact with Dawood Bhai Just call on +92322-6382012 and we'll help you. We'll solve all your problems within 12 to 24 hours and with 101% guarantee and with astrology systematic. If you want to take any personal or professional advice then also you can call us on +92322-6382012 , ONLINE LOVE PROBLEM & Other all types of Daily Life Problem's.Then CALL or WHATSAPP us on +92322-6382012 and Get all these problems solutions here by Amil Baba DAWOOD BANGALI
#vashikaranspecialist #astrologer #palmistry #amliyaat #taweez #manpasandshadi #horoscope #spiritual #lovelife #lovespell #marriagespell#aamilbabainpakistan #amilbabainkarachi #powerfullblackmagicspell #kalajadumantarspecialist #realamilbaba #AmilbabainPakistan #astrologerincanada #astrologerindubai #lovespellsmaster #kalajaduspecialist #lovespellsthatwork #aamilbabainlahore#blackmagicformarriage #aamilbaba #kalajadu #kalailam #taweez #wazifaexpert #jadumantar #vashikaranspecialist #astrologer #palmistry #amliyaat #taweez #manpasandshadi #horoscope #spiritual #lovelife #lovespell #marriagespell#aamilbabainpakistan #amilbabainkarachi #powerfullblackmagicspell #kalajadumantarspecialist #realamilbaba #AmilbabainPakistan #astrologerincanada #astrologerindubai #lovespellsmaster #kalajaduspecialist #lovespellsthatwork #aamilbabainlahore #blackmagicforlove #blackmagicformarriage #aamilbaba #kalajadu #kalailam #taweez #wazifaexpert #jadumantar #vashikaranspecialist #astrologer #palmistry #amliyaat #taweez #manpasandshadi #horoscope #spiritual #lovelife #lovespell #marriagespell#aamilbabainpakistan #amilbabainkarachi #powerfullblackmagicspell #kalajadumantarspecialist #realamilbaba #AmilbabainPakistan #astrologerincanada #astrologerindubai #lovespellsmaster #kalajaduspecialist #lovespellsthatwork #aamilbabainlahore #Amilbabainuk #amilbabainspain #amilbabaindubai #Amilbabainnorway #amilbabainkrachi #amilbabainlahore #amilbabaingujranwalan #amilbabainislamabad
Saudi Arabia stands as a titan in the global energy landscape, renowned for its abundant oil and gas resources. It's the largest exporter of petroleum and holds some of the world's most significant reserves. Let's delve into the top 10 oil and gas projects shaping Saudi Arabia's energy future in 2024.
Sachpazis:Terzaghi Bearing Capacity Estimation in simple terms with Calculati...Dr.Costas Sachpazis
Terzaghi's soil bearing capacity theory, developed by Karl Terzaghi, is a fundamental principle in geotechnical engineering used to determine the bearing capacity of shallow foundations. This theory provides a method to calculate the ultimate bearing capacity of soil, which is the maximum load per unit area that the soil can support without undergoing shear failure. The Calculation HTML Code included.
NUMERICAL SIMULATIONS OF HEAT AND MASS TRANSFER IN CONDENSING HEAT EXCHANGERS...ssuser7dcef0
Power plants release a large amount of water vapor into the
atmosphere through the stack. The flue gas can be a potential
source for obtaining much needed cooling water for a power
plant. If a power plant could recover and reuse a portion of this
moisture, it could reduce its total cooling water intake
requirement. One of the most practical way to recover water
from flue gas is to use a condensing heat exchanger. The power
plant could also recover latent heat due to condensation as well
as sensible heat due to lowering the flue gas exit temperature.
Additionally, harmful acids released from the stack can be
reduced in a condensing heat exchanger by acid condensation. reduced in a condensing heat exchanger by acid condensation.
Condensation of vapors in flue gas is a complicated
phenomenon since heat and mass transfer of water vapor and
various acids simultaneously occur in the presence of noncondensable
gases such as nitrogen and oxygen. Design of a
condenser depends on the knowledge and understanding of the
heat and mass transfer processes. A computer program for
numerical simulations of water (H2O) and sulfuric acid (H2SO4)
condensation in a flue gas condensing heat exchanger was
developed using MATLAB. Governing equations based on
mass and energy balances for the system were derived to
predict variables such as flue gas exit temperature, cooling
water outlet temperature, mole fraction and condensation rates
of water and sulfuric acid vapors. The equations were solved
using an iterative solution technique with calculations of heat
and mass transfer coefficients and physical properties.
The Internet of Things (IoT) is a revolutionary concept that connects everyday objects and devices to the internet, enabling them to communicate, collect, and exchange data. Imagine a world where your refrigerator notifies you when you’re running low on groceries, or streetlights adjust their brightness based on traffic patterns – that’s the power of IoT. In essence, IoT transforms ordinary objects into smart, interconnected devices, creating a network of endless possibilities.
Here is a blog on the role of electrical and electronics engineers in IOT. Let's dig in!!!!
For more such content visit: https://nttftrg.com/
Cosmetic shop management system project report.pdfKamal Acharya
Buying new cosmetic products is difficult. It can even be scary for those who have sensitive skin and are prone to skin trouble. The information needed to alleviate this problem is on the back of each product, but it's thought to interpret those ingredient lists unless you have a background in chemistry.
Instead of buying and hoping for the best, we can use data science to help us predict which products may be good fits for us. It includes various function programs to do the above mentioned tasks.
Data file handling has been effectively used in the program.
The automated cosmetic shop management system should deal with the automation of general workflow and administration process of the shop. The main processes of the system focus on customer's request where the system is able to search the most appropriate products and deliver it to the customers. It should help the employees to quickly identify the list of cosmetic product that have reached the minimum quantity and also keep a track of expired date for each cosmetic product. It should help the employees to find the rack number in which the product is placed.It is also Faster and more efficient way.
Immunizing Image Classifiers Against Localized Adversary Attacksgerogepatton
This paper addresses the vulnerability of deep learning models, particularly convolutional neural networks
(CNN)s, to adversarial attacks and presents a proactive training technique designed to counter them. We
introduce a novel volumization algorithm, which transforms 2D images into 3D volumetric representations.
When combined with 3D convolution and deep curriculum learning optimization (CLO), itsignificantly improves
the immunity of models against localized universal attacks by up to 40%. We evaluate our proposed approach
using contemporary CNN architectures and the modified Canadian Institute for Advanced Research (CIFAR-10
and CIFAR-100) and ImageNet Large Scale Visual Recognition Challenge (ILSVRC12) datasets, showcasing
accuracy improvements over previous techniques. The results indicate that the combination of the volumetric
input and curriculum learning holds significant promise for mitigating adversarial attacks without necessitating
adversary training.
11. HOG(glyph(
Figure 3: We visualize some high scoring detections from th
guess which are false alarms? Take a minute to study this fig
Figure 4: In this paper, we present algorithms to visualize
12. HOG
Dict
61
71
39
05
17
14
92
46
37
ersion al-
uth image
her is bet-
ull table.
Expert
0.438
(a) Human Vision (b) HOG Vision
Figure 13: HOG inversion reveals the world that object de-
tectors see. The left shows a man standing in a dark room.
14. HOG(
40 ⇥ 40 20 ⇥ 20 10 ⇥ 10 5 ⇥ 5
Figure 12: Our inversion algorithms are sensitive to the
HOG template size. We show how performance degrades
as the template becomes smaller.
cell(size(
15. nary learning.
OG basis. By
es and natural
e image basis
d V . The left
ment and the
he HOG dic-
naries.
U 2 RD⇥K
d coefficients
(5)
Original ELDA Ridge Direct PairDict
Figure 8: We show results for all four of our inversion al-
gorithms on held out image patches on similar dimensions
17. Category ELDA Ridge Direct PairDict
bicycle 0.452 0.577 0.513 0.561
bottle 0.697 0.683 0.660 0.671
car 0.668 0.677 0.652 0.639
cat 0.749 0.712 0.687 0.705
chair 0.660 0.621 0.604 0.617
table 0.656 0.617 0.582 0.614
motorbike 0.573 0.617 0.549 0.592
person 0.696 0.667 0.646 0.646
Mean 0.671 0.656 0.620 0.637
Table 1: We evaluate the performance of our inversion al-
gorithm by comparing the inverse to the ground truth image
using the mean normalized cross correlation. Higher is bet-
ter; a score of 1 is perfect. See supplemental for full table.
Category ELDA Ridge Direct PairDict Glyph Expert
bicycle 0.327 0.127 0.362 0.307 0.405 0.438
(a)
Figure 13:
tectors see.
(´ ω )
PASCAL(VOC(2011 8(
18. • Mechanical(Turks((or(Expert)
Image
HOG(
inversion
Classifier
Image
HOG(
inversion
Human
Figure 6: Inverting HOG using paired dictionary learning.
We first project the HOG vector on to a HOG basis. By
jointly learning a coupled basis of HOG features and natural
images, we then transfer the coefficients to the image basis
to recover the natural image.
Figure 7: Some pairs of dictionaries for U and V . The left
of every pair is the gray scale dictionary element and the
right is the positive components elements in the HOG dic-
tionary. Notice the correlation between dictionaries.
Suppose we write x and y in terms of bases U 2 RD⇥K
and V 2 Rd⇥K
respectively, but with shared coefficients
↵ 2 RK
:
x = U↵ and y = V ↵ (5)
The key observation is that inversion can be obtained by
Original ELDA Ridge Direct PairDict
Figure 8: We show results for all four of our inversion al-
gorithms on held out image patches on similar dimensions
common for object detection. See supplemental for more.
: Inverting HOG using paired dictionary learning.
project the HOG vector on to a HOG basis. By
earning a coupled basis of HOG features and natural
we then transfer the coefficients to the image basis
er the natural image.
: Some pairs of dictionaries for U and V . The left
pair is the gray scale dictionary element and the
he positive components elements in the HOG dic-
Notice the correlation between dictionaries.
we write x and y in terms of bases U 2 RD⇥K
2 Rd⇥K
respectively, but with shared coefficients
:
x = U↵ and y = V ↵ (5)
Original ELDA Ridge Direct PairDict
Figure 8: We show results for all four of our inversion al-
gorithms on held out image patches on similar dimensions
It’s(‘Bird’
19. The HOGgles C
Comm
False Ala
Let’s(try(Mechanical(Turk
Figure 3: We visualize some high scoring detections from the deform
guess which are false alarms? Take a minute to study this figure, then
Figure 15: We visualize a few deformable parts models trained with
ization. First row: car, person, bottle, bicycle, motorbike, potted plan
the right most visualizations, we also included the HOG glyph. Our v
20. HOG
Car
Object Detection Features⇤
masz Malisiewicz, Antonio Torralba
itute of Technology
,torralba}@csail.mit.edu
Figure 1: An image from PASCAL and a high scoring car
detection from DPM [8]. Why did the detector fail?
Figure 2: We show the crop for the false car detection from
Figure 1. On the right, we show our visualization of the
HOG features for the same patch. Our visualization reveals
that this false alarm actually looks like a car in HOG space.
Figure 2 shows the output from our visualization on the
features for the false car detection. This visualization re-
veals that, while there are clearly no cars in the original
image, there is a car hiding in the HOG descriptor. HOG
features see a slightly different visual world than what we
see, and by visualizing this space, we can gain a more intu-
itive understanding of our object detectors.
Figure 3 inverts more top detections on PASCAL for
a few categories. Can you guess which are false alarms?
Take a minute to study the figure since the next sentence
might ruin the surprise. Although every visualization looks
age from PASCAL and a high scoring car
DPM [8]. Why did the detector fail?
21. MTurk
PASCAL(VOC(2011 (
1 3
Table 1: We evaluate the performance of our inversion al-
gorithm by comparing the inverse to the ground truth image
using the mean normalized cross correlation. Higher is bet-
ter; a score of 1 is perfect. See supplemental for full table.
Category ELDA Ridge Direct PairDict Glyph Expert
bicycle 0.327 0.127 0.362 0.307 0.405 0.438
bottle 0.269 0.282 0.283 0.446 0.312 0.222
car 0.397 0.457 0.617 0.585 0.359 0.389
cat 0.219 0.178 0.381 0.199 0.139 0.286
chair 0.099 0.239 0.223 0.386 0.119 0.167
table 0.152 0.064 0.162 0.237 0.071 0.125
motorbike 0.221 0.232 0.396 0.224 0.298 0.350
person 0.458 0.546 0.502 0.676 0.301 0.375
Mean 0.282 0.258 0.355 0.383 0.191 0.233
Table 2: We evaluate visualization performance across
twenty PASCAL VOC categories by asking MTurk work-
ers to classify our inversions. Numbers are percent classi-
fied correctly; higher is better. Chance is 0.05. Glyph refers
to the standard black-and-white HOG diagram popularized
Figur
tector
If we
ously
struct
hand
with
W
classi
with
last c
better
on gl
This
itive
22. of the top
ery simi-
ent types
particular
equently,
use larger
e patches
ow when
the false
ctors fire
sualizing
the learn-
e features
0 0.2 0.4 0.6 0.8 1
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
Recall
Precision
Chair
HOG+Human AP = 0.63
RGB+Human AP = 0.96
HOG+DPM AP = 0.51
0 0.2 0.4 0.6 0.8 1
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
Recall
Precision
Cat
HOG+Human AP = 0.78
HOG+DPM AP = 0.58
0 0.2 0.4 0.6 0.8 1
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
Recall
Precision
Car
HOG+Human AP = 0.83
HOG+DPM AP = 0.87
0 0.2 0.4 0.6 0.8 1
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
Recall
Precision
Person
HOG+Human AP = 0.69
HOG+DPM AP = 0.79
Figure 14: By instructing multiple human subjects to clas-
24. • (
– [Zeiler(&(Fergus(13]
invert this, the deconvnet uses transposed versions of
the same filters, but applied to the rectified maps, not
the output of the layer beneath. In practice this means
flipping each filter vertically and horizontally.
Projecting down from higher layers uses the switch
settings generated by the max pooling in the convnet
on the way up. As these switch settings are peculiar
to a given input image, the reconstruction obtained
from a single activation thus resembles a small piece
of the original input image, with structures weighted
according to their contribution toward to the feature
activation. Since the model is trained discriminatively,
they implicitly show which parts of the input image
are discriminative. Note that these projections are not
samples from the model, since there is no generative
process involved.
Layer Below Pooled Maps
Feature Maps
Rectified Feature Maps
Convolu'onal)
Filtering){F})
Rec'fied)Linear)
Func'on)
Pooled Maps
Max)Pooling)
Reconstruction
Rectified Unpooled Maps
Unpooled Maps
Convolu'onal)
Filtering){FT})
Rec'fied)Linear)
Func'on)
Layer Above
Reconstruction
Max)Unpooling)
Switches)
Unpooling
Max Locations
“Switches”
Pooling
Pooled Maps
Feature Map
Layer Above
Reconstruction
Unpooled
Maps
Rectified
Feature Maps
Figure 1. Top: A deconvnet layer (left) attached to a con-
vnet layer (right). The deconvnet will reconstruct an ap-
proximate version of the convnet features from the layer
beneath. Bottom: An illustration of the unpooling oper-
ation in the deconvnet, using switches which record the
location of the local max in each pooling region (colored
zones) during pooling in the convnet.
Other important di↵erences relating to layers 1 and
2 were made following inspection of the visualizations
in Fig. 6, as described in Section 4.1.
The model was trained on the ImageNet 2012 train-
ing set (1.3 million images, spread over 1000 di↵erent
classes). Each RGB image was preprocessed by resiz-
ing the smallest dimension to 256, cropping the center
256x256 region, subtracting the per-pixel mean (across
all images) and then using 10 di↵erent sub-crops of size
224x224 (corners + center with(out) horizontal flips).
Stochastic gradient descent with a mini-batch size of
128 was used to update the parameters, starting with a
learning rate of 10 2
, in conjunction with a momentum
term of 0.9. We anneal the learning rate throughout
training manually when the validation error plateaus.
Dropout (Hinton et al., 2012) is used in the fully con-
nected layers (6 and 7) with a rate of 0.5. All weights
are initialized to 10 2
and biases are set to 0.
Visualization of the first layer filters during training
reveals that a few of them dominate, as shown in
Fig. 6(a). To combat this, we renormalize each filter
in the convolutional layers whose RMS value exceeds
a fixed radius of 10 1
to this fixed radius. This is cru-
cial, especially in the first layer of the model, where the
input images are roughly in the [-128,128] range. As in
(Krizhevsky et al., 2012), we produce multiple di↵er-
ent crops and flips of each training example to boost
training set size. We stopped training after 70 epochs,
which took around 12 days on a single GTX580 GPU,
using an implementation based on (Krizhevsky et al.,
2012).
4. Convnet Visualization
Using the model described in Section 3, we now use
the deconvnet to visualize the feature activations on
the ImageNet validation set.
Feature Visualization: Fig. 2 shows feature visu-
alizations from our model once training is complete.
However, instead of showing the single strongest ac-
tivation for a given feature map, we show the top 9
activations. Projecting each separately down to pixel