AI Paper Atlas

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

Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation

Tingliang Feng, Hao Shi, Xueyang Liu, Wei Feng, Liang Wan, Yanlin Zhou, Di Lin

NeurIPS 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive segmentation · 1 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 OLDM discrepancy memorization and compensation to segmentation backbone (ablation)OLDM object style compensation · GTA5->C-DrivingmIoU(T): 36.6 -> 44.1Improved
add OLDM (open domain) (ablation)OLDM object style compensation · GTA5->C-Driving openmIoU(O): 39.7 -> 46.9Improved
use global rather than local category-key features (ablation)OLDM object style compensation · GTA5->C-DrivingmIoU(T): 41.7 -> 44.1Improved
use category-key instead of mean of instance-key features (ablation)OLDM object style compensation · GTA5->C-DrivingmIoU(T): 39.2 -> 44.1Improved
update 100% of instance-key features instead of top-1 (ablation)OLDM object style compensation · GTA5->C-DrivingmIoU(T): 40.7 -> 44.1Improved
update 100% rather than top-50% instance-key features (ablation)OLDM object style compensation · GTA5->C-DrivingmIoU(T): 42.2 -> 44.1Improved
use instance-key similarity weighting instead of mean discrepancy (ablation)OLDM object style compensation · GTA5->C-DrivingmIoU(T): 37.8 -> 44.1Improved
use category-separated multi-sets instead of merged set (ablation)OLDM object style compensation · GTA5->C-DrivingmIoU(T): 39.6 -> 44.1Improved
use category-based multi-sets instead of k-means (ablation)OLDM object style compensation · GTA5->C-DrivingmIoU(T): 41.7 -> 44.1Improved
use discrepancy features instead of key discrepancy (ablation)OLDM object style compensation · GTA5->C-DrivingmIoU(T): 42.7 -> 44.1Improved
weight discrepancy by instance similarity at test time instead of averaging (ablation)OLDM object style compensation · GTA5->C-DrivingmIoU(T): 40.7 -> 44.1Improved
add pseudo annotations from final compensated features (ablation)OLDM object style compensation · GTA5->C-DrivingmIoU(T): 39.7 -> 44.1Improved

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