AI Paper Atlas

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

OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation

Ding Zhong, Xu Zheng, Chenfei Liao, Yuanhuiyi Lyu, Jialei Chen, Shengyang Wu, Linfeng Zhang, Xuming Hu

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive segmentation · 23 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 self-supervised pseudo-label loss (ablation)OmniSAM-B · CS13-to-DP13mIoU: 56.49 -> 57.06Improved
add FPA loss on top of pseudo-label loss (static labels) (ablation)OmniSAM-B · CS13-to-DP13mIoU: 57.06 -> 58.29Improved
add dynamic pseudo-label update (no FPA) (ablation)OmniSAM-B · CS13-to-DP13mIoU: 57.06 -> 60.60Improved
add FPA loss to full config with dynamic updates (ablation)OmniSAM-B · CS13-to-DP13mIoU: 60.60 -> 62.46Improved
add self-supervised pseudo-label loss (ablation)OmniSAM-L · SPin8-to-SPan8mIoU: 76.85 -> 77.36Improved
add FPA loss without pseudo-label update (ablation)OmniSAM-L · SPin8-to-SPan8mIoU: 77.36 -> 77.10No clear effect
add dynamic pseudo-label update (no FPA) (ablation)OmniSAM-L · SPin8-to-SPan8mIoU: 77.36 -> 79.06Improved
add FPA loss to dynamic-update config (ablation)OmniSAM-L · SPin8-to-SPan8mIoU: 79.06 -> 77.79Hurt
add FPA loss weight lambda=0.1 (vs 0) (ablation)OmniSAM-B · CS13-to-DP13mIoU: 56.49 -> 62.46Improved
raise lambda from 0.1 to 1.0 (ablation)OmniSAM-B · CS13-to-DP13mIoU: 62.46 -> 60.90Hurt
add memory attention (ablation)OmniSAM-L · SPin8-to-SPan8mIoU: 78.02 -> 79.06Improved
add memory attention (ablation)OmniSAM-B · SPin8-to-SPan8mIoU: 73.09 -> 74.72Improved

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