Papers › Focal and Global Knowledge Distillation for Detectors

Focal and Global Knowledge Distillation for Detectors

23 Nov 2021CVPR 2022 1arXiv:2111.11837archive 2025-07-28

Zhendong Yang, Zhe Li, Xiaohu Jiang, Yuan Gong, Zehuan Yuan, Danpei Zhao, Chun Yuan

Knowledge distillation has been applied to image classification successfully. However, object detection is much more sophisticated and most knowledge distillation methods have failed on it. In this paper, we point out that in object detection, the features of the teacher and student vary greatly in different areas, especially in the foreground and background. If we distill them equally, the uneven differences between feature maps will negatively affect the distillation. Thus, we propose Focal and Global Distillation (FGD). Focal distillation separates the foreground and background, forcing the student to focus on the teacher's critical pixels and channels. Global distillation rebuilds the relation between different pixels and transfers it from teachers to students, compensating for missing global information in focal distillation. As our method only needs to calculate the loss on the feature map, FGD can be applied to various detectors. We experiment on various detectors with different backbones and the results show that the student detector achieves excellent mAP improvement. For example, ResNet-50 based RetinaNet, Faster RCNN, RepPoints and Mask RCNN with our distillation method achieve 40.7%, 42.0%, 42.0% and 42.1% mAP on COCO2017, which are 3.3, 3.6, 3.4 and 2.9 higher than the baseline, respectively. Our codes are available at https://github.com/yzd-v/FGD.

PaperPDFConference PDFCode

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

Code

yzd-v/FGD officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

Image ClassificationKnowledge DistillationObject Detectionimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Knowledge Distillation COCO (Common Objects in Context) ADLIK-Faster (T: Faster R-CNN vit-base S: Faster R-CNN deit-small) box AP 47.6 #1 of 4 Archive leaderboard report
Knowledge Distillation COCO (Common Objects in Context) ADLIK-Mask (T: Mask R-CNN vit-base S: Mask R-CNN deit-small) mask AP 42.4 #2 of 4 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.

Methods

1x1 ConvolutionConvolutionFPNFocal LossKnowledge DistillationRepPointsRetinaNet

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