Papers › Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection

Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection

15 Dec 2020CVPR 2021 1arXiv:2012.08548archive 2025-07-28

Jingru Tan, Xin Lu, Gang Zhang, Changqing Yin, Quanquan Li

Recently proposed decoupled training methods emerge as a dominant paradigm for long-tailed object detection. But they require an extra fine-tuning stage, and the disjointed optimization of representation and classifier might lead to suboptimal results. However, end-to-end training methods, like equalization loss (EQL), still perform worse than decoupled training methods. In this paper, we reveal the main issue in long-tailed object detection is the imbalanced gradients between positives and negatives, and find that EQL does not solve it well. To address the problem of imbalanced gradients, we introduce a new version of equalization loss, called equalization loss v2 (EQL v2), a novel gradient guided reweighing mechanism that re-balances the training process for each category independently and equally. Extensive experiments are performed on the challenging LVIS benchmark. EQL v2 outperforms origin EQL by about 4 points overall AP with 14-18 points improvements on the rare categories. More importantly, it also surpasses decoupled training methods. Without further tuning for the Open Images dataset, EQL v2 improves EQL by 7.3 points AP, showing strong generalization ability. Codes have been released at https://github.com/tztztztztz/eqlv2

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

tztztztztz/eqlv2 officialmentioned in papertf report
FenHua/Robust_Logo_Detection mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Instance SegmentationLong-tailed Object DetectionObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation LVIS v1.0 val Cascade-R101-EQLv2 mask AP 28.8 #18 of 25 Archive leaderboard report
Instance Segmentation LVIS v1.0 val R101-FPN-MaskRCNN-EQLv2 mask AP 27.5 #21 of 25 Archive leaderboard report
Instance Segmentation LVIS v1.0 val R50-FPN-MaskRCNN-EQLv2 mask AP 23.7 #24 of 25 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections