-
Notifications
You must be signed in to change notification settings - Fork 9.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Feature] Support DDOD: Disentangle Your Dense Object Detector(ACM MM2021 oral) #7279
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
hhaAndroid
reviewed
Feb 28, 2022
chhluo
reviewed
Feb 28, 2022
chhluo
reviewed
Feb 28, 2022
chhluo
reviewed
Feb 28, 2022
chhluo
reviewed
Feb 28, 2022
Please run |
@Irvingao You can resolve conflicts before proceeding with further development. |
hhaAndroid
reviewed
Mar 1, 2022
hhaAndroid
reviewed
Mar 1, 2022
hhaAndroid
reviewed
Mar 1, 2022
hhaAndroid
reviewed
Mar 1, 2022
hhaAndroid
reviewed
Mar 1, 2022
hhaAndroid
reviewed
Mar 1, 2022
hhaAndroid
reviewed
Mar 1, 2022
hhaAndroid
reviewed
Mar 1, 2022
hhaAndroid
reviewed
Mar 1, 2022
hhaAndroid
reviewed
Mar 1, 2022
Kindly ping @Irvingao to resolve the conflict. Furthermore, will there be any progress in the following weeks? |
Please solve the conflicts and rebase on the latest dev branch |
chhluo
reviewed
May 3, 2022
hhaAndroid
reviewed
May 10, 2022
hhaAndroid
reviewed
May 18, 2022
chhluo
reviewed
May 18, 2022
hhaAndroid
approved these changes
May 24, 2022
ZwwWayne
reviewed
May 24, 2022
ZwwWayne
approved these changes
May 24, 2022
ZwwWayne
pushed a commit
that referenced
this pull request
Jul 18, 2022
…2021 oral) (#7279) * add ddod feature * add ddod feature * modify new * [Feature] modify ddod code0225 * [Feature] modify ddod code0226 * [Feature] modify ddod code0228 * [Feature] modify ddod code0228#7279 * [Feature] modify ddod code0301 * [Feature] modify ddod code0301 test draft * [Feature] modify ddod code0301 test * [Feature] modify ddod code0301 extra * [Feature] modify ddod code0301 delete src/mmtrack * [Feature] modify ddod code0302 * [Feature] modify ddod code0302(2) * [Feature] modify ddod code0303 * [Feature] modify ddod code0303(2) * [Feature] modify ddod code0303(3) * [Feature] modify ddod code0305 * [Feature] modify ddod code0305(2) delete diou * [Feature] modify ddod code0305(3) * modify ddod code0306 * [Feature] modify ddod code0307 * [Feature] modify ddod code0311 * [Feature] modify ddod code0311(2) * [Feature] modify ddod code0313 * update * [Feature] modify ddod code0319 * fix * fix lint * [Feature] modify ddod code0321 * update readme * [0502] compute common vars at once for get_target * [0504] update ddod conflicts * [0518] seperate reg and cls loss and get_target compute * [0518] merge ATSSCostAssigner to ATSSAssigner * [0518] refine ATSSAssigner * [0518] refine ATSSAssigner 2 * [0518] refine ATSSAssigner 2 * [0518] refine ATSSAssigner 3 * [0519] fix bugs * update * fix lr * update weight Co-authored-by: hha <1286304229@qq.com>
ZwwWayne
pushed a commit
to ZwwWayne/mmdetection
that referenced
this pull request
Jul 19, 2022
…2021 oral) (open-mmlab#7279) * add ddod feature * add ddod feature * modify new * [Feature] modify ddod code0225 * [Feature] modify ddod code0226 * [Feature] modify ddod code0228 * [Feature] modify ddod code0228#7279 * [Feature] modify ddod code0301 * [Feature] modify ddod code0301 test draft * [Feature] modify ddod code0301 test * [Feature] modify ddod code0301 extra * [Feature] modify ddod code0301 delete src/mmtrack * [Feature] modify ddod code0302 * [Feature] modify ddod code0302(2) * [Feature] modify ddod code0303 * [Feature] modify ddod code0303(2) * [Feature] modify ddod code0303(3) * [Feature] modify ddod code0305 * [Feature] modify ddod code0305(2) delete diou * [Feature] modify ddod code0305(3) * modify ddod code0306 * [Feature] modify ddod code0307 * [Feature] modify ddod code0311 * [Feature] modify ddod code0311(2) * [Feature] modify ddod code0313 * update * [Feature] modify ddod code0319 * fix * fix lint * [Feature] modify ddod code0321 * update readme * [0502] compute common vars at once for get_target * [0504] update ddod conflicts * [0518] seperate reg and cls loss and get_target compute * [0518] merge ATSSCostAssigner to ATSSAssigner * [0518] refine ATSSAssigner * [0518] refine ATSSAssigner 2 * [0518] refine ATSSAssigner 2 * [0518] refine ATSSAssigner 3 * [0519] fix bugs * update * fix lr * update weight Co-authored-by: hha <1286304229@qq.com>
ZwwWayne
pushed a commit
to ZwwWayne/mmdetection
that referenced
this pull request
Jul 19, 2022
…2021 oral) (open-mmlab#7279) * add ddod feature * add ddod feature * modify new * [Feature] modify ddod code0225 * [Feature] modify ddod code0226 * [Feature] modify ddod code0228 * [Feature] modify ddod code0228#7279 * [Feature] modify ddod code0301 * [Feature] modify ddod code0301 test draft * [Feature] modify ddod code0301 test * [Feature] modify ddod code0301 extra * [Feature] modify ddod code0301 delete src/mmtrack * [Feature] modify ddod code0302 * [Feature] modify ddod code0302(2) * [Feature] modify ddod code0303 * [Feature] modify ddod code0303(2) * [Feature] modify ddod code0303(3) * [Feature] modify ddod code0305 * [Feature] modify ddod code0305(2) delete diou * [Feature] modify ddod code0305(3) * modify ddod code0306 * [Feature] modify ddod code0307 * [Feature] modify ddod code0311 * [Feature] modify ddod code0311(2) * [Feature] modify ddod code0313 * update * [Feature] modify ddod code0319 * fix * fix lint * [Feature] modify ddod code0321 * update readme * [0502] compute common vars at once for get_target * [0504] update ddod conflicts * [0518] seperate reg and cls loss and get_target compute * [0518] merge ATSSCostAssigner to ATSSAssigner * [0518] refine ATSSAssigner * [0518] refine ATSSAssigner 2 * [0518] refine ATSSAssigner 2 * [0518] refine ATSSAssigner 3 * [0519] fix bugs * update * fix lr * update weight Co-authored-by: hha <1286304229@qq.com>
SakiRinn
pushed a commit
to SakiRinn/mmdetection-locount
that referenced
this pull request
Mar 17, 2023
…2021 oral) (open-mmlab#7279) * add ddod feature * add ddod feature * modify new * [Feature] modify ddod code0225 * [Feature] modify ddod code0226 * [Feature] modify ddod code0228 * [Feature] modify ddod code0228#7279 * [Feature] modify ddod code0301 * [Feature] modify ddod code0301 test draft * [Feature] modify ddod code0301 test * [Feature] modify ddod code0301 extra * [Feature] modify ddod code0301 delete src/mmtrack * [Feature] modify ddod code0302 * [Feature] modify ddod code0302(2) * [Feature] modify ddod code0303 * [Feature] modify ddod code0303(2) * [Feature] modify ddod code0303(3) * [Feature] modify ddod code0305 * [Feature] modify ddod code0305(2) delete diou * [Feature] modify ddod code0305(3) * modify ddod code0306 * [Feature] modify ddod code0307 * [Feature] modify ddod code0311 * [Feature] modify ddod code0311(2) * [Feature] modify ddod code0313 * update * [Feature] modify ddod code0319 * fix * fix lint * [Feature] modify ddod code0321 * update readme * [0502] compute common vars at once for get_target * [0504] update ddod conflicts * [0518] seperate reg and cls loss and get_target compute * [0518] merge ATSSCostAssigner to ATSSAssigner * [0518] refine ATSSAssigner * [0518] refine ATSSAssigner 2 * [0518] refine ATSSAssigner 2 * [0518] refine ATSSAssigner 3 * [0519] fix bugs * update * fix lr * update weight Co-authored-by: hha <1286304229@qq.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Disentangle Your Dense Object Detector
Abstract
Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding. However, the current training pipeline for dense detectors is compromised to lots of conjunctions that may not hold. In this paper, we investigate three such important conjunctions: 1) only samples assigned as positive in classification head are used to train the regression head; 2) classification and regression share the same input feature and computational fields defined by the parallel head architecture; and 3) samples distributed in different feature pyramid layers are treated equally when computing the loss. We first carry out a series of pilot experiments to show disentangling such conjunctions can lead to persistent performance improvement. Then, based on these findings, we propose Disentangled Dense Object Detector(DDOD), in which simple and effective disentanglement mechanisms are designed and integrated into the current state-of-the-art dense object detectors. Extensive experiments on MS COCO benchmark show that our approach can lead to 2.0 mAP, 2.4 mAP and 2.2 mAP absolute improvements on RetinaNet, FCOS, and ATSS baselines with negligible extra overhead. Notably, our best model reaches 55.0 mAP on the COCO test-dev set and 93.5 AP on the hard subset of WIDER FACE, achieving new state-of-the-art performance on these two competitive benchmarks. Code is available at https://github.com/zehuichen123/DDOD.
Results and Models
Citation
Checklist
It's the second PR of DDOD from PR#7227 , which changes branch from master to dev. Other changes are as follow:
ddod_r50_fp16_1x_coco.py
._base _
to replace repeated code in the config file.diou
calculation function to bbox_overlaps.@torch.no_grad()
to function.DDODHead
docs.Log