Mixing
Possible regression losses for object detection
.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty{ height:90px;width:728px;box-sizing:border-box;
}
Many object detection algorithms predict bounding boxes as (xmin, ymin, xmax, ymax) meaning the top-left and the bottom-right corner of a bounding box. Besides, in order to avoid exploding gradients the majority of the papers suggest smooth L1 loss or simply L1 loss.
My question is, are there any successful attempts of other approaches?
For instance
- Predict the top-left point (x,y), the width and the height of the box.
- Predict the center point (x,y), the width and the height of the box.
- Predict the center point (x,y), the size and the aspect ratio of the box.
- Predict the center point (x,y), the size and tan-1(aspect ratio)
Moreover, some of these options might include different importance / weights for some attributes. E.g. it might be more important to find a good center point and size than a well-fitted aspect ratio. Also, it might be wise to use L1 loss for the center point but L2 for size or aspect ratio. Is there any research on this topic you know about?
Thanks.
neural-network computer-vision object-detection bounding-box loss-function
asked Jan 3 at 13:59
Gergely PappGergely Papp
8515
add a comment |
Many object detection algorithms predict bounding boxes as (xmin, ymin, xmax, ymax) meaning the top-left and the bottom-right corner of a bounding box. Besides, in order to avoid exploding gradients the majority of the papers suggest smooth L1 loss or simply L1 loss.
My question is, are there any successful attempts of other approaches?
For instance
- Predict the top-left point (x,y), the width and the height of the box.
- Predict the center point (x,y), the width and the height of the box.
- Predict the center point (x,y), the size and the aspect ratio of the box.
- Predict the center point (x,y), the size and tan-1(aspect ratio)
Moreover, some of these options might include different importance / weights for some attributes. E.g. it might be more important to find a good center point and size than a well-fitted aspect ratio. Also, it might be wise to use L1 loss for the center point but L2 for size or aspect ratio. Is there any research on this topic you know about?
Thanks.
neural-network computer-vision object-detection bounding-box loss-function
asked Jan 3 at 13:59
Gergely PappGergely Papp
8515
add a comment |
Many object detection algorithms predict bounding boxes as (xmin, ymin, xmax, ymax) meaning the top-left and the bottom-right corner of a bounding box. Besides, in order to avoid exploding gradients the majority of the papers suggest smooth L1 loss or simply L1 loss.
My question is, are there any successful attempts of other approaches?
For instance
- Predict the top-left point (x,y), the width and the height of the box.
- Predict the center point (x,y), the width and the height of the box.
- Predict the center point (x,y), the size and the aspect ratio of the box.
- Predict the center point (x,y), the size and tan-1(aspect ratio)
Moreover, some of these options might include different importance / weights for some attributes. E.g. it might be more important to find a good center point and size than a well-fitted aspect ratio. Also, it might be wise to use L1 loss for the center point but L2 for size or aspect ratio. Is there any research on this topic you know about?
Thanks.
neural-network computer-vision object-detection bounding-box loss-function
asked Jan 3 at 13:59
Gergely PappGergely Papp
8515
Many object detection algorithms predict bounding boxes as (xmin, ymin, xmax, ymax) meaning the top-left and the bottom-right corner of a bounding box. Besides, in order to avoid exploding gradients the majority of the papers suggest smooth L1 loss or simply L1 loss.
My question is, are there any successful attempts of other approaches?
For instance
- Predict the top-left point (x,y), the width and the height of the box.
- Predict the center point (x,y), the width and the height of the box.
- Predict the center point (x,y), the size and the aspect ratio of the box.
- Predict the center point (x,y), the size and tan-1(aspect ratio)
Moreover, some of these options might include different importance / weights for some attributes. E.g. it might be more important to find a good center point and size than a well-fitted aspect ratio. Also, it might be wise to use L1 loss for the center point but L2 for size or aspect ratio. Is there any research on this topic you know about?
Thanks.
neural-network computer-vision object-detection bounding-box loss-function
neural-network computer-vision object-detection bounding-box loss-function
asked Jan 3 at 13:59
Gergely PappGergely Papp
8515
asked Jan 3 at 13:59
Gergely PappGergely Papp
8515
asked Jan 3 at 13:59
Gergely PappGergely Papp
8515
asked Jan 3 at 13:59
Gergely PappGergely Papp
8515
asked Jan 3 at 13:59
Gergely PappGergely Papp
8515
8515
add a comment |
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
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: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
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
});
}
});
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%2fstackoverflow.com%2fquestions%2f54023777%2fpossible-regression-losses-for-object-detection%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
Thanks for contributing an answer to Stack Overflow!
- 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.
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%2fstackoverflow.com%2fquestions%2f54023777%2fpossible-regression-losses-for-object-detection%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
