Trjtdtk

Open a doc from terminal, but not by its name

Query about absorption line spectra

Freedom of speech and where it applies

A book (mid 2000s) about a kid getting an old laptop that connects him to aliens, the alien government (I think) coming after him?

Mutated beetles cartoons (characters made of rope and rings)

Multiplicative persistence

Why do we read the Megillah by night and by day?

Why is it that I can sometimes guess the next note?

GraphicsGrid with a Label for each Column and Row

Do Legal Documents Require Signing In Standard Pen Colors?

How to explain what's wrong with this application of the chain rule?

Has any country ever had 2 former presidents in jail simultaneously?

Is '大勢の人' redundant?

Can not upgrade Kali,not enough space in /var/cache/apt/archives

Create all possible words using a set or letters

What should you do if you miss a job interview (deliberately)?

What is the difference between "Do you interest" and "...interested in" something?

MTG Artifact and Enchantment Rulings

Are the IPv6 address space and IPv4 address space completely disjoint?

Drawing ramified coverings with tikz

Does a 'pending' US visa application constitute a denial?

Footnote and citation at the end of a sentence

Count the occurrence of each unique word in the file

A social experiment. What is the worst that can happen?

How to visualise GIST features of an image

Match an image from a set of images : Combine traditional Computer vision + Deep Learning/CNNspeech accent recognition data augmentation and trainingIs it possible to design a deep CNN model on a small size image datasetAdvantages of one shot learning over image classificationHow to add non-image features along side images as the input of CNNsDetecting if an image can be made BW/Greyscale/ColourCNN to learn and visualize 2d featuresit is possible to use features maps of CNN to localised important areas in image?Image classification using Semantic Segmented ImagesDesigning a pretrained DNN for image similarity

2

$begingroup$

I am currently working on a image classification application using deep learning algorithms (either by using GIST features or CNN). I need help in understanding the below queries.

1. I have extracted the GIST features of an image (Reference Link : https://github.com/tuttieee/lear-gist-python). These extracted features will be given as input to deep learning algorithm to classify the images.
   Is there a way to visualize the extracted features on top of the image?




2. CNN or GIST, Which is better for image classification? Is GIST outdated when compared to CNN?

Thank you,
KK

deep-learning cnn image-classification

share|improve this question

asked Mar 20 at 4:56

KK2491KK2491

343219

$endgroup$

add a comment | 

2

$begingroup$

I am currently working on a image classification application using deep learning algorithms (either by using GIST features or CNN). I need help in understanding the below queries.

1. I have extracted the GIST features of an image (Reference Link : https://github.com/tuttieee/lear-gist-python). These extracted features will be given as input to deep learning algorithm to classify the images.
   Is there a way to visualize the extracted features on top of the image?




2. CNN or GIST, Which is better for image classification? Is GIST outdated when compared to CNN?

Thank you,
KK

deep-learning cnn image-classification

share|improve this question

asked Mar 20 at 4:56

KK2491KK2491

343219

$endgroup$

add a comment | 

$begingroup$

I am currently working on a image classification application using deep learning algorithms (either by using GIST features or CNN). I need help in understanding the below queries.

1. I have extracted the GIST features of an image (Reference Link : https://github.com/tuttieee/lear-gist-python). These extracted features will be given as input to deep learning algorithm to classify the images.
   Is there a way to visualize the extracted features on top of the image?




2. CNN or GIST, Which is better for image classification? Is GIST outdated when compared to CNN?

Thank you,
KK

deep-learning cnn image-classification

share|improve this question

asked Mar 20 at 4:56

KK2491KK2491

343219

$endgroup$

share|improve this question

asked Mar 20 at 4:56

KK2491KK2491

343219

share|improve this question

asked Mar 20 at 4:56

KK2491KK2491

343219

asked Mar 20 at 4:56

KK2491KK2491

343219

asked Mar 20 at 4:56

KK2491KK2491

343219

1 Answer
1

active

oldest

votes

0

$begingroup$

Given that code is trivial for both (GIST + Network and Raw Pixel + Network), you can try three approaches for a given project.

1. GIST + Dense layers (GIST is not space-distributed)


2. Raw Pixels + CNN + Dense Layers


3. Raw pixels + CNN + Dense + input layer 2 (GIST) + Dense

For some projects, GIST can help since it is an abstract feature that CNN might or might not learn.

EDIT : Following paper compares GIST and CNN

https://arxiv.org/pdf/1504.05241.pdf

Regarding :

Is there a way to visualize the extracted features on top of the image?

This can be done with an attention layer in approach 3 (CNN + GIST).

CNN provides spacial distribution (Required for visualization) and dense layer that merges CNN's output with GIST can be used with an attention layer.

Paper for visualization : https://arxiv.org/abs/1502.03044

share|improve this answer

edited Mar 20 at 9:54

answered Mar 20 at 9:48

Shamit VermaShamit Verma

91929

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Added some details on visualization
  $endgroup$
  – Shamit Verma
  Mar 20 at 9:55
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Thank you for the information. Really helped me understanding the concepts. Will check the feasibility of implementation and update you here.
  $endgroup$
  – KK2491
  Mar 21 at 3:04
  

  
  
  
  

add a comment | 

Your Answer

StackExchange.ifUsing("editor", function ()
return StackExchange.using("mathjaxEditing", function ()
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix)
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
);
);
, "mathjax-editing");

StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "557"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);

StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);

else
createEditor();

);

function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);



);

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);

Sign up using Google

Sign up using Facebook

Sign up using Email and Password

Post as a guest

Name

Email

Required, but never shown

StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f47651%2fhow-to-visualise-gist-features-of-an-image%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

0

$begingroup$

Given that code is trivial for both (GIST + Network and Raw Pixel + Network), you can try three approaches for a given project.

1. GIST + Dense layers (GIST is not space-distributed)


2. Raw Pixels + CNN + Dense Layers


3. Raw pixels + CNN + Dense + input layer 2 (GIST) + Dense

For some projects, GIST can help since it is an abstract feature that CNN might or might not learn.

EDIT : Following paper compares GIST and CNN

https://arxiv.org/pdf/1504.05241.pdf

Regarding :

Is there a way to visualize the extracted features on top of the image?

This can be done with an attention layer in approach 3 (CNN + GIST).

CNN provides spacial distribution (Required for visualization) and dense layer that merges CNN's output with GIST can be used with an attention layer.

Paper for visualization : https://arxiv.org/abs/1502.03044

share|improve this answer

edited Mar 20 at 9:54

answered Mar 20 at 9:48

Shamit VermaShamit Verma

91929

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Added some details on visualization
  $endgroup$
  – Shamit Verma
  Mar 20 at 9:55
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Thank you for the information. Really helped me understanding the concepts. Will check the feasibility of implementation and update you here.
  $endgroup$
  – KK2491
  Mar 21 at 3:04
  

  
  
  
  

add a comment | 

0

$begingroup$

Given that code is trivial for both (GIST + Network and Raw Pixel + Network), you can try three approaches for a given project.

1. GIST + Dense layers (GIST is not space-distributed)


2. Raw Pixels + CNN + Dense Layers


3. Raw pixels + CNN + Dense + input layer 2 (GIST) + Dense

For some projects, GIST can help since it is an abstract feature that CNN might or might not learn.

EDIT : Following paper compares GIST and CNN

https://arxiv.org/pdf/1504.05241.pdf

Regarding :

Is there a way to visualize the extracted features on top of the image?

This can be done with an attention layer in approach 3 (CNN + GIST).

CNN provides spacial distribution (Required for visualization) and dense layer that merges CNN's output with GIST can be used with an attention layer.

Paper for visualization : https://arxiv.org/abs/1502.03044

share|improve this answer

edited Mar 20 at 9:54

answered Mar 20 at 9:48

Shamit VermaShamit Verma

91929

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Added some details on visualization
  $endgroup$
  – Shamit Verma
  Mar 20 at 9:55
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Thank you for the information. Really helped me understanding the concepts. Will check the feasibility of implementation and update you here.
  $endgroup$
  – KK2491
  Mar 21 at 3:04
  

  
  
  
  

add a comment | 

$begingroup$

Given that code is trivial for both (GIST + Network and Raw Pixel + Network), you can try three approaches for a given project.

1. GIST + Dense layers (GIST is not space-distributed)


2. Raw Pixels + CNN + Dense Layers


3. Raw pixels + CNN + Dense + input layer 2 (GIST) + Dense

For some projects, GIST can help since it is an abstract feature that CNN might or might not learn.

EDIT : Following paper compares GIST and CNN

https://arxiv.org/pdf/1504.05241.pdf

Regarding :

Is there a way to visualize the extracted features on top of the image?

This can be done with an attention layer in approach 3 (CNN + GIST).

CNN provides spacial distribution (Required for visualization) and dense layer that merges CNN's output with GIST can be used with an attention layer.

Paper for visualization : https://arxiv.org/abs/1502.03044

share|improve this answer

edited Mar 20 at 9:54

answered Mar 20 at 9:48

Shamit VermaShamit Verma

91929

$endgroup$

share|improve this answer

edited Mar 20 at 9:54

answered Mar 20 at 9:48

Shamit VermaShamit Verma

91929

answered Mar 20 at 9:48

Shamit VermaShamit Verma

91929

answered Mar 20 at 9:48

Shamit VermaShamit Verma

91929