Papers › KS-DETR: Knowledge Sharing in Attention Learning for Detection Transformer

KS-DETR: Knowledge Sharing in Attention Learning for Detection Transformer

22 Feb 2023arXiv:2302.11208archive 2025-07-28

Kaikai Zhao, Norimichi Ukita

Scaled dot-product attention applies a softmax function on the scaled dot-product of queries and keys to calculate weights and then multiplies the weights and values. In this work, we study how to improve the learning of scaled dot-product attention to improve the accuracy of DETR. Our method is based on the following observations: using ground truth foreground-background mask (GT Fg-Bg Mask) as additional cues in the weights/values learning enables learning much better weights/values; with better weights/values, better values/weights can be learned. We propose a triple-attention module in which the first attention is a plain scaled dot-product attention, the second/third attention generates high-quality weights/values (with the assistance of GT Fg-Bg Mask) and shares the values/weights with the first attention to improve the quality of values/weights. The second and third attentions are removed during inference. We call our method knowledge-sharing DETR (KS-DETR), which is an extension of knowledge distillation (KD) in the way that the improved weights and values of the teachers (the second and third attentions) are directly shared, instead of mimicked, by the student (the first attention) to enable more efficient knowledge transfer from the teachers to the student. Experiments on various DETR-like methods show consistent improvements over the baseline methods on the MS COCO benchmark. Code is available at https://github.com/edocanonymous/KS-DETR.

Paper PDF Code

Code

edocanonymous/ks-detr officialmentioned in paperpytorch 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

Knowledge Distillation Transfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position Encodings Adam Attention BPE Convolution Dense Connections Detr Dropout Feedforward Network Knowledge Distillation Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

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