AI Paper Atlas

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

Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability

Boyong He, Yuxiang Ji, Zhuoyue Tan, Liaoni Wu

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 4 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 consistency loss between auxiliary and ordinary branch (ablation)Diff. detector · FoggyCityscapesmAP: 45.8 -> 50.7Improved
add consistency loss between auxiliary and ordinary branch (ablation)Diff. detector · Cityscapes in-domainmAP: 62.4 -> 61.1Hurt
add noise adding in single-step diffusion (ablation)Diff. detector · Foggy. cross-domainmAP: 30.8 -> 34.9Improved
add feature collection and fusion (ablation)Diff. detector · Cityscapes in-domainmAP: 38.5 -> 52.4Improved
add object-centered auxiliary branch (ablation)Diff. detector · ClipartmAP: 43.6 -> 53.3Improved
use single-step diffusion instead of five stepsGDD · CityscapesmAP: 59.8 -> 36.8Hurt
vary consistency weight gamma from 0.0 to 1.0 (ablation)Diff. detector · FoggyCityscapesmAP: 47.6 -> 50.7Improved
increase gamma from 1.0 to 2.0 (ablation)Diff. detector · FoggyCityscapesmAP: 50.7 -> 49.1Hurt
add feature alignment on top of domain augmentation (ablation)Diff. guided detector DG · BDD100KmAP: 36.2 -> 39.5Improved
add object alignment (pseudo-labels) for DG guided detector (ablation)Diff. guided detector DG · BDD100KmAP: 39.5 -> 46.7Improved
add object alignment for DA guided detector (ablation)Diff. guided detector DA · BDD100KmAP: 40.2 -> 51.3Improved
add domain augmentation (ablation)Diff. guided detector DG · BDD100KmAP: 25.4 -> 36.2Improved

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