Can we do convolutions on binary mask inputs?
$begingroup$
I am training a vehicle trajectory prediction algorithm using Deep MaxEnt Inverse Reinforcement Learning (https://arxiv.org/abs/1507.04888). My intention is to have as input to this algorithm a top-down semantic grid of the environment which I obtain from a combination of raw images, HD maps and perception algorithms. Specifically, for each class (e.g. road, road marking, pavement, etc.), I have a binary mask of the grid telling me whether each coordinate contains that class or not.
Essentially (without going into the details of Deep MaxEnt IRL) I will have an FCN which takes in the environmental data and outputs the predicted reward map for the environment. I would like to pass in my binary semantic masks instead of the raw data that is usually used for these problems (e.g. RGB images, LIDAR statistics, etc.). My question is whether anyone knows of any reason why this would not work? Is performing convolutions on binary masks rather than a range of continuous floating point values (e.g. RGB values) a problem in any way? I realise that I will not require as many convolutional layers compared to a raw data input due to the fact that the perception/detection/segmentation on the raw data has already been done, but overall is this a viable approach?
machine-learning deep-learning convnet reinforcement-learning convolution
asked 3 hours ago
MarkMark
1
New contributor
Mark 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 am training a vehicle trajectory prediction algorithm using Deep MaxEnt Inverse Reinforcement Learning (https://arxiv.org/abs/1507.04888). My intention is to have as input to this algorithm a top-down semantic grid of the environment which I obtain from a combination of raw images, HD maps and perception algorithms. Specifically, for each class (e.g. road, road marking, pavement, etc.), I have a binary mask of the grid telling me whether each coordinate contains that class or not.
Essentially (without going into the details of Deep MaxEnt IRL) I will have an FCN which takes in the environmental data and outputs the predicted reward map for the environment. I would like to pass in my binary semantic masks instead of the raw data that is usually used for these problems (e.g. RGB images, LIDAR statistics, etc.). My question is whether anyone knows of any reason why this would not work? Is performing convolutions on binary masks rather than a range of continuous floating point values (e.g. RGB values) a problem in any way? I realise that I will not require as many convolutional layers compared to a raw data input due to the fact that the perception/detection/segmentation on the raw data has already been done, but overall is this a viable approach?
machine-learning deep-learning convnet reinforcement-learning convolution
asked 3 hours ago
MarkMark
1
New contributor
Mark 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 am training a vehicle trajectory prediction algorithm using Deep MaxEnt Inverse Reinforcement Learning (https://arxiv.org/abs/1507.04888). My intention is to have as input to this algorithm a top-down semantic grid of the environment which I obtain from a combination of raw images, HD maps and perception algorithms. Specifically, for each class (e.g. road, road marking, pavement, etc.), I have a binary mask of the grid telling me whether each coordinate contains that class or not.
Essentially (without going into the details of Deep MaxEnt IRL) I will have an FCN which takes in the environmental data and outputs the predicted reward map for the environment. I would like to pass in my binary semantic masks instead of the raw data that is usually used for these problems (e.g. RGB images, LIDAR statistics, etc.). My question is whether anyone knows of any reason why this would not work? Is performing convolutions on binary masks rather than a range of continuous floating point values (e.g. RGB values) a problem in any way? I realise that I will not require as many convolutional layers compared to a raw data input due to the fact that the perception/detection/segmentation on the raw data has already been done, but overall is this a viable approach?
machine-learning deep-learning convnet reinforcement-learning convolution
asked 3 hours ago
MarkMark
1
New contributor
Mark is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
I am training a vehicle trajectory prediction algorithm using Deep MaxEnt Inverse Reinforcement Learning (https://arxiv.org/abs/1507.04888). My intention is to have as input to this algorithm a top-down semantic grid of the environment which I obtain from a combination of raw images, HD maps and perception algorithms. Specifically, for each class (e.g. road, road marking, pavement, etc.), I have a binary mask of the grid telling me whether each coordinate contains that class or not.
Essentially (without going into the details of Deep MaxEnt IRL) I will have an FCN which takes in the environmental data and outputs the predicted reward map for the environment. I would like to pass in my binary semantic masks instead of the raw data that is usually used for these problems (e.g. RGB images, LIDAR statistics, etc.). My question is whether anyone knows of any reason why this would not work? Is performing convolutions on binary masks rather than a range of continuous floating point values (e.g. RGB values) a problem in any way? I realise that I will not require as many convolutional layers compared to a raw data input due to the fact that the perception/detection/segmentation on the raw data has already been done, but overall is this a viable approach?
machine-learning deep-learning convnet reinforcement-learning convolution
machine-learning deep-learning convnet reinforcement-learning convolution
asked 3 hours ago
MarkMark
1
New contributor
Mark is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 3 hours ago
MarkMark
1
New contributor
Mark is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 3 hours ago
MarkMark
1
New contributor
Mark is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 3 hours ago
MarkMark
1
asked 3 hours ago
MarkMark
1
1
New contributor
Mark is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
Mark is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
Mark 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
});
}
});
Mark 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%2f45262%2fcan-we-do-convolutions-on-binary-mask-inputs%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
Mark is a new contributor. Be nice, and check out our Code of Conduct.
Mark is a new contributor. Be nice, and check out our Code of Conduct.
Mark is a new contributor. Be nice, and check out our Code of Conduct.
Mark 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%2f45262%2fcan-we-do-convolutions-on-binary-mask-inputs%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
