Learning image embddings for clustering based on custom distance metric
$begingroup$
I have a large dataset of images, and i can calculate their distance to oneanother. I will at a later point recieve new images where i can not determine their distances to the ones in my training set(or anyone else for that matter). My idea was to cluster these images, and then infer similar features for the new images, as those in the same cluster. I tried using the vgg16, vgg19, and resnet50 to encode the images and then use DBSCAN to cluster. It worked decently, however from my experience, DBSCAN does not work optimally in such a high dimensional space.
I found this on here
Another way is to learn an embedding that optimizes your similarity metric using a neural network and just cluster that
But i am not sure what is meant here, how exactly should i train the network, in my mind i would have to define a loss function that punishes bad encodings. I though of simply taking the square distance between the calculated distance, and the distance in the encoded space, however i feel like there are multiple issues with that.
I am most comfortable with keras, so if anybody know a repo or something along those lines, i would be grateful aswell!
python neural-network deep-learning image-recognition
New contributor
$endgroup$
add a comment |
$begingroup$
I have a large dataset of images, and i can calculate their distance to oneanother. I will at a later point recieve new images where i can not determine their distances to the ones in my training set(or anyone else for that matter). My idea was to cluster these images, and then infer similar features for the new images, as those in the same cluster. I tried using the vgg16, vgg19, and resnet50 to encode the images and then use DBSCAN to cluster. It worked decently, however from my experience, DBSCAN does not work optimally in such a high dimensional space.
I found this on here
Another way is to learn an embedding that optimizes your similarity metric using a neural network and just cluster that
But i am not sure what is meant here, how exactly should i train the network, in my mind i would have to define a loss function that punishes bad encodings. I though of simply taking the square distance between the calculated distance, and the distance in the encoded space, however i feel like there are multiple issues with that.
I am most comfortable with keras, so if anybody know a repo or something along those lines, i would be grateful aswell!
python neural-network deep-learning image-recognition
New contributor
$endgroup$
add a comment |
$begingroup$
I have a large dataset of images, and i can calculate their distance to oneanother. I will at a later point recieve new images where i can not determine their distances to the ones in my training set(or anyone else for that matter). My idea was to cluster these images, and then infer similar features for the new images, as those in the same cluster. I tried using the vgg16, vgg19, and resnet50 to encode the images and then use DBSCAN to cluster. It worked decently, however from my experience, DBSCAN does not work optimally in such a high dimensional space.
I found this on here
Another way is to learn an embedding that optimizes your similarity metric using a neural network and just cluster that
But i am not sure what is meant here, how exactly should i train the network, in my mind i would have to define a loss function that punishes bad encodings. I though of simply taking the square distance between the calculated distance, and the distance in the encoded space, however i feel like there are multiple issues with that.
I am most comfortable with keras, so if anybody know a repo or something along those lines, i would be grateful aswell!
python neural-network deep-learning image-recognition
New contributor
$endgroup$
I have a large dataset of images, and i can calculate their distance to oneanother. I will at a later point recieve new images where i can not determine their distances to the ones in my training set(or anyone else for that matter). My idea was to cluster these images, and then infer similar features for the new images, as those in the same cluster. I tried using the vgg16, vgg19, and resnet50 to encode the images and then use DBSCAN to cluster. It worked decently, however from my experience, DBSCAN does not work optimally in such a high dimensional space.
I found this on here
Another way is to learn an embedding that optimizes your similarity metric using a neural network and just cluster that
But i am not sure what is meant here, how exactly should i train the network, in my mind i would have to define a loss function that punishes bad encodings. I though of simply taking the square distance between the calculated distance, and the distance in the encoded space, however i feel like there are multiple issues with that.
I am most comfortable with keras, so if anybody know a repo or something along those lines, i would be grateful aswell!
python neural-network deep-learning image-recognition
python neural-network deep-learning image-recognition
New contributor
New contributor
New contributor
asked 2 days ago
kumalkakumalka
61
61
New contributor
New contributor
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
});
}
});
kumalka 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%2f47234%2flearning-image-embddings-for-clustering-based-on-custom-distance-metric%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
kumalka is a new contributor. Be nice, and check out our Code of Conduct.
kumalka is a new contributor. Be nice, and check out our Code of Conduct.
kumalka is a new contributor. Be nice, and check out our Code of Conduct.
kumalka 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%2f47234%2flearning-image-embddings-for-clustering-based-on-custom-distance-metric%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