AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Beyond Single Images: Retrieval Self-Augmented Unsupervised Camouflaged Object Detection

Ji Du, Xin Wang, Fangwei Hao, Mingyang Yu, Chunyuan Chen, Jiesheng Wu, Bin Wang, Jing Xu, Ping Li

ICCV 2025 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 5 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 dataset-level retrieval over image-level spectral clustering (ablation)RISE · COD10KS-measure: 0.641 -> 0.763Improved
add cross-category retrieval (ablation)RISE · COD10KS-measure: 0.710 -> 0.763Improved
add cross-category retrieval (ablation)RISE · COD10Kweighted F-measure: 0.518 -> 0.600Improved
add histogram-based image filtering (ablation)RISE · COD10KS-measure: 0.744 -> 0.763Improved
add histogram-based image filtering (ablation)RISE · COD10Kweighted F-measure: 0.575 -> 0.600Improved
add multi-view KNN retrieval (ablation)RISE · COD10KS-measure: 0.759 -> 0.763Improved
add multi-view KNN retrieval (ablation)RISE · CHAMELEONS-measure: 0.829 -> 0.822Hurt
add histogram-based image filtering (ablation)RISE · CHAMELEONS-measure: 0.820 -> 0.822No clear effect
integrate RISE into KMeans clustering (ablation)KMeans · COD10KS-measure: 0.400 -> 0.723Improved
integrate RISE into GMM clustering (ablation)GMM · COD10KS-measure: 0.450 -> 0.719Improved
integrate RISE into hierarchical clustering (ablation)HCA · COD10KS-measure: 0.474 -> 0.733Improved
integrate RISE into TokenCut (ablation)TokenCut · COD10KS-measure: 0.682 -> 0.769Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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