AI Paper Atlas

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

MTTrans: Cross-Domain Object Detection with Mean Teacher Transformer

Jinze Yu, Jiaming Liu, Xiaobao Wei, Haoyi Zhou, Yohei Nakata, Denis Gudovskiy, Tomoyuki Okuno, Jianxin Li, Kurt Keutzer, Shanghang Zhang

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 72 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 framework with pseudo labels (ablation)Deformable DETR · Cityscapes to Foggy CityscapesmAP50: 28.5 -> 35.843 (+7.34)Improved
add multi-level feature alignment on top of mean teacher (ablation)MT-DefDETR · Cityscapes to Foggy CityscapesmAP50: 35.843 -> 43.413Improved
add DQFA on encoder (ablation)MTTrans · Cityscapes to Foggy CityscapesmAP50: 43.183 -> 43.413Improved
add DQFA on decoder (ablation)MTTrans · Cityscapes to Foggy CityscapesmAP50: 42.962 -> 43.413Improved
add TIFA on encoder (ablation)MTTrans · Cityscapes to Foggy CityscapesmAP50: 43.013 -> 43.413Improved
add BGPA on decoder (ablation)MTTrans · Cityscapes to Foggy CityscapesmAP50: 43.003 -> 43.413Improved
use BGPA instead of TIFA for decoder alignment (ablation)MTTrans · Cityscapes to Foggy CityscapesmAP50: 42.953 -> 43.413Improved
use TIFA instead of BGPA for encoder alignment (ablation)MTTrans · Cityscapes to Foggy CityscapesmAP50: 43.068 -> 43.413Improved
share object queries between teacher and student (ablation)MTTrans · Cityscapes to Foggy CityscapesmAP50: 42.797 -> 43.413Improved
MTTrans versus SFA on synthetic to realDeformable DETR · Sim10k to Cityscapescar AP: 52.6 -> 57.9Improved
MTTrans versus SFA on scene adaptationDeformable DETR · Cityscapes to BDD100k daytimemAP50: 28.9 -> 32.6Improved
MTTrans versus ViSGA on weather adaptationMTTrans · Cityscapes to Foggy CityscapesmAP50: 43.3 -> 43.4No clear effect

Later papers that compared with this method

4 later accepted papers report MTTrans as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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