AI Paper Atlas

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

Rethinking Detecting Salient and Camouflaged Objects in Unconstrained Scenes

Zhangjun Zhou, Yiping Li, Chunlin Zhong, Jianuo Huang, Jialun Pei, Hua Li, He Tang

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 8 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 Intra-SPQ (ablation)USCNet ARM · USC12K overall scenesmIoU: 75.31 -> 78.03Improved
add Inter-SPQ (ablation)USCNet ARM · USC12K overall scenesmIoU: 76.96 -> 78.03Improved
add Intra-SPQ (ablation)USCNet ARM · USC12K overall scenesCSCS: 9.07 -> 7.49Improved
add Q2I and I2Q attention (ablation)USCNet ARM · USC12K overall scenesmIoU: 74.77 -> 78.03Improved
add Q2I and I2Q attention (ablation)USCNet ARM · USC12K overall scenesCSCS: 9.85 -> 7.49Improved
add I2Q attention (ablation)USCNet ARM · USC12K overall scenesCSCS: 8.52 -> 7.49Improved
add ARM with frozen mask decoder to SAM2-Adapter (ablation)USCNet · USC12K overall scenesmIoU: 74.98 -> 78.03Improved
tune the encoder with adapters instead of freezing it (ablation)SAM2 baseline · USC12K overall scenesmIoU: 68.78 -> 74.98Improved
train SOD model ICON on USC12KICON on COD datasets · COD10Kweighted F-measure false detection: 0.6384 -> 0.0146Improved
train COD model SINet-V2 on USC12KSINet-V2 on SOD datasets · DUTSweighted F-measure false detection: 0.7412 -> 0.0708Improved
train unified VSCode on USC12K with COD promptVSCode on SOD datasets · HKU-ISweighted F-measure false detection: 0.8733 -> 0.0391Improved
use USCNet instead of VSCodeunified model generalization · NC4KF_beta max: .626 -> .794Improved

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