Papers › Revisiting the Loss Weight Adjustment in Object Detection

Revisiting the Loss Weight Adjustment in Object Detection

17 Mar 2021arXiv:2103.09488archive 2025-07-28

Wenxin Yu, Xueling Shen, Jiajie Hu, Dong Yin

Object detection is a typical multi-task learning application, which optimizes classification and regression simultaneously. However, classification loss always dominates the multi-task loss in anchor-based methods, hampering the consistent and balanced optimization of the tasks. In this paper, we find that shifting the bounding boxes can change the division of positive and negative samples in classification, meaning classification depends on regression. Moreover, we summarize three important conclusions about fine-tuning loss weights, considering different datasets, optimizers and regression loss functions. Based on the above conclusions, we propose Adaptive Loss Weight Adjustment(ALWA) to solve the imbalance in optimizing anchor-based methods according to statistical characteristics of losses. By incorporating ALWA into previous state-of-the-art detectors, we achieve a significant performance gain on PASCAL VOC and MS COCO, even with L1, SmoothL1 and CIoU loss. The code is available at https://github.com/ywx-hub/ALWA.

PaperPDFCode

Code

ywx-hub/ALWA officialmentioned in paper 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

ClassificationGeneral ClassificationMulti-Task LearningObjectObject Detectionobject-detectionregression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adaptive Loss

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