Channels in convolutional layer
$begingroup$
I usually see convolutions performed over all the channels of the input. For example a $3x3$ kernel is really a $3x3xN$ kernel for a an input with $N$ channels, thus resulting in a single output channel per filter.
What would happen, if you were to do a convolution on individual channels or pairs of channels instead, with independent filters per channel? I am wondering if when certain channels are not correlated could you prevent some information loss by keeping the channels separate for some layers?
machine-learning neural-network cnn convolution kernel
asked yesterday
dadrakedadrake
61
New contributor
dadrake 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 usually see convolutions performed over all the channels of the input. For example a $3x3$ kernel is really a $3x3xN$ kernel for a an input with $N$ channels, thus resulting in a single output channel per filter.
What would happen, if you were to do a convolution on individual channels or pairs of channels instead, with independent filters per channel? I am wondering if when certain channels are not correlated could you prevent some information loss by keeping the channels separate for some layers?
machine-learning neural-network cnn convolution kernel
asked yesterday
dadrakedadrake
61
New contributor
dadrake 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 usually see convolutions performed over all the channels of the input. For example a $3x3$ kernel is really a $3x3xN$ kernel for a an input with $N$ channels, thus resulting in a single output channel per filter.
What would happen, if you were to do a convolution on individual channels or pairs of channels instead, with independent filters per channel? I am wondering if when certain channels are not correlated could you prevent some information loss by keeping the channels separate for some layers?
machine-learning neural-network cnn convolution kernel
asked yesterday
dadrakedadrake
61
New contributor
dadrake is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
I usually see convolutions performed over all the channels of the input. For example a $3x3$ kernel is really a $3x3xN$ kernel for a an input with $N$ channels, thus resulting in a single output channel per filter.
What would happen, if you were to do a convolution on individual channels or pairs of channels instead, with independent filters per channel? I am wondering if when certain channels are not correlated could you prevent some information loss by keeping the channels separate for some layers?
machine-learning neural-network cnn convolution kernel
machine-learning neural-network cnn convolution kernel
asked yesterday
dadrakedadrake
61
New contributor
dadrake is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked yesterday
dadrakedadrake
61
New contributor
dadrake is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked yesterday
dadrakedadrake
61
New contributor
dadrake is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked yesterday
dadrakedadrake
61
asked yesterday
dadrakedadrake
61
61
New contributor
dadrake is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
dadrake is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
dadrake 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 |
1 Answer
1
active
oldest
votes
$begingroup$
The technique you have mentioned is called "Depth-wise Separable Convolutions" and it relies on the idea that spatial and depth-wise information can be decoupled. Its main advantage is that compared with standard convolution, since it doesn't need to perform convolution across all channels, it has considerably less connections, (so less parameters) which results in a lighter model.
There is an architecture named "Xception" ("Extreme version of Inception") by Google that uses a version of such convolutional layers and produces close to state-of-the-art results. There is a really good review of it at Towards Data Science.
Personally I don't like the idea of decoupling the channels, because I think it gets us a less "sophisticated" model, but it seems to work so who am I to judge?
answered 20 hours ago
Mark.FMark.F
891318
$endgroup$
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
});
}
});
dadrake 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%2f46435%2fchannels-in-convolutional-layer%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
The technique you have mentioned is called "Depth-wise Separable Convolutions" and it relies on the idea that spatial and depth-wise information can be decoupled. Its main advantage is that compared with standard convolution, since it doesn't need to perform convolution across all channels, it has considerably less connections, (so less parameters) which results in a lighter model.
There is an architecture named "Xception" ("Extreme version of Inception") by Google that uses a version of such convolutional layers and produces close to state-of-the-art results. There is a really good review of it at Towards Data Science.
Personally I don't like the idea of decoupling the channels, because I think it gets us a less "sophisticated" model, but it seems to work so who am I to judge?
answered 20 hours ago
Mark.FMark.F
891318
$endgroup$
add a comment |
$begingroup$
The technique you have mentioned is called "Depth-wise Separable Convolutions" and it relies on the idea that spatial and depth-wise information can be decoupled. Its main advantage is that compared with standard convolution, since it doesn't need to perform convolution across all channels, it has considerably less connections, (so less parameters) which results in a lighter model.
There is an architecture named "Xception" ("Extreme version of Inception") by Google that uses a version of such convolutional layers and produces close to state-of-the-art results. There is a really good review of it at Towards Data Science.
Personally I don't like the idea of decoupling the channels, because I think it gets us a less "sophisticated" model, but it seems to work so who am I to judge?
answered 20 hours ago
Mark.FMark.F
891318
$endgroup$
add a comment |
$begingroup$
The technique you have mentioned is called "Depth-wise Separable Convolutions" and it relies on the idea that spatial and depth-wise information can be decoupled. Its main advantage is that compared with standard convolution, since it doesn't need to perform convolution across all channels, it has considerably less connections, (so less parameters) which results in a lighter model.
There is an architecture named "Xception" ("Extreme version of Inception") by Google that uses a version of such convolutional layers and produces close to state-of-the-art results. There is a really good review of it at Towards Data Science.
Personally I don't like the idea of decoupling the channels, because I think it gets us a less "sophisticated" model, but it seems to work so who am I to judge?
answered 20 hours ago
Mark.FMark.F
891318
$endgroup$
The technique you have mentioned is called "Depth-wise Separable Convolutions" and it relies on the idea that spatial and depth-wise information can be decoupled. Its main advantage is that compared with standard convolution, since it doesn't need to perform convolution across all channels, it has considerably less connections, (so less parameters) which results in a lighter model.
There is an architecture named "Xception" ("Extreme version of Inception") by Google that uses a version of such convolutional layers and produces close to state-of-the-art results. There is a really good review of it at Towards Data Science.
Personally I don't like the idea of decoupling the channels, because I think it gets us a less "sophisticated" model, but it seems to work so who am I to judge?
answered 20 hours ago
Mark.FMark.F
891318
answered 20 hours ago
Mark.FMark.F
891318
answered 20 hours ago
Mark.FMark.F
891318
answered 20 hours ago
Mark.FMark.F
891318
891318
add a comment |
add a comment |
dadrake is a new contributor. Be nice, and check out our Code of Conduct.
dadrake is a new contributor. Be nice, and check out our Code of Conduct.
dadrake is a new contributor. Be nice, and check out our Code of Conduct.
dadrake 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%2f46435%2fchannels-in-convolutional-layer%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
