AI Paper Atlas

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

Bidirectional Alignment for Domain Adaptive Detection with Transformers

Liqiang He, Wei Wang, Albert Chen, Min Sun, Cheng-Hao Kuo, Sinisa Todorovic

ICCV 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 35 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 BiADT bidirectional domain-invariant/specific alignment over AQTDAB-Deformable-DETR · Cityscapes->FoggyCityscapesmAP50: 47.4 -> 49.4Improved
add object-level alignments to backbone alignment (ablation)BiADT · Cityscapes->FoggyCityscapesmAP50: 38.3 -> 42.9Improved
add image-level alignments to backbone alignment (ablation)BiADT · Cityscapes->FoggyCityscapesmAP50: 38.3 -> 44.4Improved
combine object and image alignments (ablation)BiADT · Cityscapes->FoggyCityscapesmAP50: 44.4 -> 48.2Improved
add DyHinge loss (ablation)BiADT · Cityscapes->FoggyCityscapesmAP50: 48.2 -> 48.7Improved
add mutual information loss (ablation)BiADT · Cityscapes->FoggyCityscapesmAP50: 48.7 -> 49.4Improved
add AQT alignments to BiADTBiADT · Cityscapes->FoggyCityscapesmAP50: 49.4 -> 49.8Improved
integrate BiADT into teacher-student framework with pseudo-labelsBiADT · Cityscapes->FoggyCityscapesmAP50: 49.4 -> 50.8Improved
use Conditional-DETR instead of Dab-Deformable-DETR detector (ablation)BiADT · Cityscapes->FoggyCityscapesmAP50: 49.4 -> 27.8Hurt
use Dab-Deformable-DETR instead of Deformable-DETR (ablation)BiADT · Cityscapes->FoggyCityscapesmAP50: 48.9 -> 49.4Improved
compare BiADT with pseudo-label methodsBiADT · Cityscapes->FoggyCityscapesmAP50: 49.4 vs AT 50.9Mixed

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