AI Paper Atlas

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

Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection

Chaoqi Chen, Jiongcheng Li, Hong-Yu Zhou, Xiaoguang Han, Yue Huang, Xinghao Ding, Yizhou Yu

TPAMI 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 51 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
upgrade DBGL to FGRR (foreground-aware relational reasoning)DBGL · Pascal VOC to ClipartmAP: 41.6% -> 43.3%Improved
upgrade DBGL to FGRRDBGL · Pascal VOC to Watercolor2kmAP: 53.8% -> 55.7%Improved
upgrade DBGL to FGRRDBGL · Pascal VOC to Comic2kmAP: 29.7% -> 32.7%Improved
upgrade DBGL to FGRRDBGL · Public to In-house mammogramAP on mass: 38.4 -> 43.9Improved
model intra and inter-domain relations instead of MTOR object relation consistencyMTOR · Cityscapes to Foggy-CityscapesmAP: 35.1% -> 40.8%Improved
use relational reasoning instead of prototype alignment (C2F, GPA)C2F and GPA · Cityscapes to Foggy-CityscapesmAP: 38.6% and 39.5% -> 40.8%Improved
add FPN to the detection backboneDAOD methods · Sim10K to CityscapesAP on car: 44.5 -> 55.8Improved
apply FGRR adaptation versus no adaptationFaster-RCNN ResNet-101 · Public to In-house mammogramAP on mass: 12.0 -> 43.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

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