AI Paper Atlas

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

Unsupervised Domain Adaptation for One-Stage Object Detector Using Offsets to Bounding Box

Jayeon Yoo, Inseop Chung, Nojun Kwak

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 32 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 offset-aware conditioning (left offset) instead of global alignment onlyFCOS domain-adaptive detector · Cityscapes to Foggy CityscapesmAP@0.5: 37.5 -> 42.6Improved
condition on both left and top offsets instead of left only (ablation)OADA · Cityscapes to Foggy CityscapesmAP@0.5: 42.6 -> 44.8Improved
add self-training initialized from OADA pre-trained modelOADA (Offset-Left & Top) · Cityscapes to Foggy CityscapesmAP@0.5: 44.8 -> 45.4Improved
add self-trainingOADA (Offset-Left & Top) · Sim10k to CityscapesmAP@0.5: 56.6 -> 59.2Improved
add self-trainingOADA (Offset-Left & Top) · KITTI to CityscapesmAP@0.5: 46.3 -> 47.8Improved
smooth the offset probability with alpha0=0.2 rather than none (ablation)OADA (Offset-Left & Top) · Cityscapes to Foggy CityscapesmAP@0.5: 42.6 -> 44.8Improved
use offset-aware conditioning rather than uniform vector (alpha0=1.0) (ablation)OADA (Offset-Left & Top) · Cityscapes to Foggy CityscapesmAP@0.5: 42.6 -> 44.8Improved
use 3 offset bins instead of 1 (ablation)OADA (Offset-Left & Top) · Cityscapes to Foggy CityscapesmAP@0.5: 42.4 -> 44.8Improved
increase offset bins from 3 to 5 (ablation)OADA (Offset-Left & Top) · Cityscapes to Foggy CityscapesmAP@0.5: 44.8 -> 41.4Hurt
use confidence threshold rho=0.3 instead of 0.0 (ablation)OADA (Offset-Top) · Cityscapes to Foggy CityscapesmAP@0.5: 37.0 -> 42.7Improved
use confidence threshold rho=0.5 instead of 0.0 (ablation)OADA (Offset-Top) · Sim10k to CityscapesmAP@0.5: 48.5 -> 55.7Improved
use confidence threshold rho=0.5 instead of 0.0 (ablation)OADA (Offset-Top) · KITTI to CityscapesmAP@0.5: 43.8 -> 45.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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