AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Teach-DETR: Better Training DETR With Teachers

Linjiang Huang, Kaixin Lu, Guanglu Song, Liang Wang, Si Liu, Yu Liu, Hongsheng Li

TPAMI 2023 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 17 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
distill features with FKDH-Def-DETR student · MSCOCO val (H-Deformable-DETR Swin-S, 12 ep)AP: 52.5 -> 52.0Hurt
distill features with FGDH-Def-DETR student · MSCOCO val (H-Deformable-DETR Swin-S, 12 ep)AP: 52.5 -> 51.7Hurt
add teacher box auxiliary supervision with scoresH-Def-DETR student · MSCOCO val (H-Deformable-DETR Swin-S, 12 ep)AP: 52.5 -> 53.5Improved
concatenate GT and auxiliary boxes (ablation)H-Def-DETR student · MSCOCO val (H-Deformable-DETR Swin-S, 12 ep)AP: 52.5 -> 41.9Hurt
match GT and teacher boxes in parallel instead of concatenating (ablation)Teach-DETR · MSCOCO val (H-Deformable-DETR Swin-S, 12 ep)AP: 41.9 -> 53.1Improved
weight auxiliary supervision by teacher confidence scores (ablation)Teach-DETR · MSCOCO val (H-Deformable-DETR Swin-S, 12 ep)AP: 53.1 -> 53.5Improved
use teacher labels instead of GT labels (ablation)Teach-DETR · MSCOCO val (H-Deformable-DETR Swin-S, 12 ep)AP: 53.2 -> 53.5Improved
use teacher confidence scores instead of IoUs (ablation)Teach-DETR · MSCOCO val (H-Deformable-DETR Swin-S, 12 ep)AP: 53.3 -> 53.5Improved
use noisy boxes in place of teacher boxes (ablation)H-Def-DETR student · MSCOCO val (H-Deformable-DETR Swin-S, 12 ep)AP: 52.5 -> 51.9Hurt
use soft labels instead of hard labels (ablation)Teach-DETR · MSCOCO val (H-Deformable-DETR Swin-S, 12 ep)AP: 53.5 -> 46.8Hurt
use online instead of offline teachers (ablation)Teach-DETR · MSCOCO val (H-Deformable-DETR Swin-S, 12 ep)AP: 53.5 -> 53.6No clear effect
apply auxiliary supervision to all layers instead of final decoder layer only (ablation)Teach-DETR · MSCOCO val (H-Deformable-DETR Swin-S, 12 ep)AP: 52.7 -> 53.5Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy