AI Paper Atlas

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

Rethinking Pseudo-Labels: Multi-Granularity Supervision for Domain Adaptive Object Detection

Haohao Ma, Weimin Lu, Qiqi Ge

ECCV 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 0 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 image-level supervision (ablation)AT (instance-level only) · Pascal VOC -> Clipart1kmAP50: 45.7 -> 46.1Mixed
add instance-level supervision to image-level supervision (ablation)MGPL image-level only · Pascal VOC -> Clipart1kmAP50: 46.1 -> 50.6Improved
combine image-level and instance-level supervision (ablation)AT · Pascal VOC -> Clipart1kmAP50: 45.7 -> 50.6Improved
add coarse-to-fine collaborative filtering (ablation)MGPL w/o Filter · Pascal VOC -> Clipart1kmAP50: 50.6 -> 51.4Improved
increase lambda_img from 0.1 to 0.5 (ablation)MGPL · Pascal VOC -> Clipart1kmAP50: 48.5 -> 51.4Improved
increase lambda_img from 0.5 to 2.0 (ablation)MGPL · Pascal VOC -> Clipart1kmAP50: 51.4 -> 50.8Hurt
use MGPL instead of AT under fully flipped pseudo-box class labelsAT · Pascal VOC -> Clipart1k (noise ratio 1.0)mAP50 gap: +5.7% -> +9.3%Improved
inject full pseudo-label noise (flip all box class labels)AT · Pascal VOC -> Clipart1kmAP50: 45.7 -> 38.6Hurt
inject full pseudo-label noise (flip all box class labels)MGPL w/o Filter · Pascal VOC -> Clipart1kmAP50 change: -4.5%Hurt
use MGPL instead of CMTCMT · Cityscapes -> Foggy CityscapesmAP50: 51.9 -> 52.7Improved
use MGPL instead of CMTCMT · KITTI -> Cityscapes (car)AP50 car: 64.3 -> 64.3No clear effect

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