AI Paper Atlas

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

CLP: A Real-World Dataset of Contaminated Lens Protectors for Robust Semantic Segmentation

Sungyong Park, Sooyoung Choi, Hyunsuh Koh, Youngjae Choi, Heewon Kim

CVPR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation

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
train on clean images only with domain generalization (SoMA, Rein) instead of domain adaptation with unlabeled contaminated imagessegmentation models · CLP testmIoU: +14.0 (SoMA) and +12.9 (Rein) mIoU over best DA baselineImproved
use frozen DINOv2 foundation encoder with Mask2Former decoderMask2Former · CLP test overallmIoU: 36.4 -> 47.2Improved
use frozen SAM encoder instead of DINOv2Mask2Former · CLP test overallmIoU: 47.2 -> 39.2Hurt
use RobustSAM encoder instead of SAMSAM + Mask2Former · CLP mudmIoU: 30.2 -> 33.6Improved
apply FIFO fog-invariant trainingsegmentation · CLP test overallmIoU: 36.4 -> 32.2Hurt
add generic pretrained URIE restoration before Mask2Former (ablation)Mask2Former · CLP test overallmIoU: 33.9 -> 32.2Hurt
add DiffUIR restoration (best PSNR) before Mask2Former (ablation)Mask2Former · CLP test overallmIoU: 33.9 -> 35.7; water -1.9, mud -0.3, condensation +2.4Mixed
add task-aware UniRestore before Mask2Former (ablation)Mask2Former · CLP test overallmIoU: 33.9 -> 35.5 (+1.6)Improved
add NAFNet restoration before Mask2Former (ablation)Mask2Former · CLP test overallmIoU: 33.9 -> 33.7Hurt
increase training data from 10% to 100% of CLP scenes (ablation)SoMA · CLP testmIoU: 22.19 -> 48.69Improved
increase training data from 10% to 100% of CLP scenes (ablation)NAFNet · CLP test restorationPSNR: 24.63 -> 25.77Improved
increase lens-to-protector distance 0 to 5 cm under mudMask2Former · CLP mudmIoU: 34.5 -> 26.1Hurt

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