Generating class saliency maps using deep ConvNets
$begingroup$
I'm trying to generate some image-specific class saliency maps using a trained convolutional neural network as described in this paper. Basically it computes the derivative of the input image with respect to the output class score, then those gradients can be served as a saliency map.
The authors in this paper use softmax as output layer so each class corresponds to a single neuron in the output layer. However my model is used to do binary classification and my output layer is a single neuron followed by a sigmoid unit, does it make sense that I use this method to get the saliency maps for both classes? If so, should I just use back-propagation to calculate the derivative of the input image with respect to the output score for both 0 and 1 classes?
Thanks!
deep-learning
asked 4 mins ago
DerickShiDerickShi
11
New contributor
DerickShi is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
I'm trying to generate some image-specific class saliency maps using a trained convolutional neural network as described in this paper. Basically it computes the derivative of the input image with respect to the output class score, then those gradients can be served as a saliency map.
The authors in this paper use softmax as output layer so each class corresponds to a single neuron in the output layer. However my model is used to do binary classification and my output layer is a single neuron followed by a sigmoid unit, does it make sense that I use this method to get the saliency maps for both classes? If so, should I just use back-propagation to calculate the derivative of the input image with respect to the output score for both 0 and 1 classes?
Thanks!
deep-learning
asked 4 mins ago
DerickShiDerickShi
11
New contributor
DerickShi is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
I'm trying to generate some image-specific class saliency maps using a trained convolutional neural network as described in this paper. Basically it computes the derivative of the input image with respect to the output class score, then those gradients can be served as a saliency map.
The authors in this paper use softmax as output layer so each class corresponds to a single neuron in the output layer. However my model is used to do binary classification and my output layer is a single neuron followed by a sigmoid unit, does it make sense that I use this method to get the saliency maps for both classes? If so, should I just use back-propagation to calculate the derivative of the input image with respect to the output score for both 0 and 1 classes?
Thanks!
deep-learning
asked 4 mins ago
DerickShiDerickShi
11
New contributor
DerickShi is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
I'm trying to generate some image-specific class saliency maps using a trained convolutional neural network as described in this paper. Basically it computes the derivative of the input image with respect to the output class score, then those gradients can be served as a saliency map.
The authors in this paper use softmax as output layer so each class corresponds to a single neuron in the output layer. However my model is used to do binary classification and my output layer is a single neuron followed by a sigmoid unit, does it make sense that I use this method to get the saliency maps for both classes? If so, should I just use back-propagation to calculate the derivative of the input image with respect to the output score for both 0 and 1 classes?
Thanks!
deep-learning
deep-learning
asked 4 mins ago
DerickShiDerickShi
11
New contributor
DerickShi is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 4 mins ago
DerickShiDerickShi
11
New contributor
DerickShi is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 4 mins ago
DerickShiDerickShi
11
New contributor
DerickShi is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 4 mins ago
DerickShiDerickShi
11
asked 4 mins ago
DerickShiDerickShi
11
11
New contributor
DerickShi is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
DerickShi is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
DerickShi is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
add a comment |
add a comment |
0
active
oldest
votes
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
});
}
});
DerickShi is a new contributor. Be nice, and check out our Code of Conduct.
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
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f46236%2fgenerating-class-saliency-maps-using-deep-convnets%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
DerickShi is a new contributor. Be nice, and check out our Code of Conduct.
DerickShi is a new contributor. Be nice, and check out our Code of Conduct.
DerickShi is a new contributor. Be nice, and check out our Code of Conduct.
DerickShi is a new contributor. Be nice, and check out our Code of Conduct.
Thanks for contributing an answer to Data Science Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
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
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f46236%2fgenerating-class-saliency-maps-using-deep-convnets%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
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
Required, but never shown
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
Required, but never shown
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
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
