AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Dynamic Retraining-Updating Mean Teacher for Source-Free Object Detection

Trinh Le Ba Khanh, Huy-Hung Nguyen, Long Hoang Pham, Duong Nguyen-Ngoc Tran, Jae Wook Jeon

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 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
add Mean Teacher self-training to source-only model (ablation)Deformable DETR · Cityscapes -> Foggy CityscapesmAP: 29.5 -> 37.4Improved
add masked image consistency (MIC) to MT (ablation)MT · Cityscapes -> Foggy CityscapesmAP: 37.4 -> 39.8Improved
add Historical Student Loss (ablation)MT + MIC · Cityscapes -> Foggy CityscapesmAP: 39.8 -> 41.3Improved
add Dynamic Retraining-Updating on top of Historical Student Loss (ablation)MT + MIC + L_his · Cityscapes -> Foggy CityscapesmAP: 41.3 -> 43.6Improved
add DRU without Historical Student Loss (ablation)MT + MIC · Cityscapes -> Foggy CityscapesmAP: 39.8 -> 40.9Improved
re-initialize decoder only instead of backbone+encoder (ablation)DRU student retraining · Cityscapes -> Foggy CityscapesmAP: 39.9 -> 43.6Improved
re-initialize backbone+encoder instead of continuing training (ablation)DRU student retraining · Cityscapes -> Foggy CityscapesmAP: 41.2 -> 39.9Hurt
dynamic teacher update interval instead of fixed interval (ablation)DRU · Cityscapes -> Foggy CityscapesmAP: 43.4 (i=5) -> 43.6Improved
vary meta-iteration M from 5 to 2 or 20 (ablation)DRU · Cityscapes -> Foggy CityscapesmAP: 43.6 -> 41.9 (M=2), 41.5 (M=20)Hurt
DRU vs previous SFOD methodsDRU · Cityscapes -> BDD100kmAP: 31.6 -> 36.6Improved

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