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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add dataset-level retrieval over image-level spectral clustering (ablation) | RISE · COD10K | S-measure: 0.641 -> 0.763 | Improved |
| add cross-category retrieval (ablation) | RISE · COD10K | S-measure: 0.710 -> 0.763 | Improved |
| add cross-category retrieval (ablation) | RISE · COD10K | weighted F-measure: 0.518 -> 0.600 | Improved |
| add histogram-based image filtering (ablation) | RISE · COD10K | S-measure: 0.744 -> 0.763 | Improved |
| add histogram-based image filtering (ablation) | RISE · COD10K | weighted F-measure: 0.575 -> 0.600 | Improved |
| add multi-view KNN retrieval (ablation) | RISE · COD10K | S-measure: 0.759 -> 0.763 | Improved |
| add multi-view KNN retrieval (ablation) | RISE · CHAMELEON | S-measure: 0.829 -> 0.822 | Hurt |
| add histogram-based image filtering (ablation) | RISE · CHAMELEON | S-measure: 0.820 -> 0.822 | No clear effect |
| integrate RISE into KMeans clustering (ablation) | KMeans · COD10K | S-measure: 0.400 -> 0.723 | Improved |
| integrate RISE into GMM clustering (ablation) | GMM · COD10K | S-measure: 0.450 -> 0.719 | Improved |
| integrate RISE into hierarchical clustering (ablation) | HCA · COD10K | S-measure: 0.474 -> 0.733 | Improved |
| integrate RISE into TokenCut (ablation) | TokenCut · COD10K | S-measure: 0.682 -> 0.769 | Improved |
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.
- ProMerge — ProMerge: Prompt and Merge for Unsupervised Instance Segmentation (ECCV 2024) · better on 9 of 9 shared results
- TokenCut — TokenCut: Segmenting Objects in Images and Videos With Self-Supervised Transformer and Normalized Cut (TPAMI 2023) · better on 1 of 1 shared result
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
- Camouflaged Object Detection (CVPR 2020 · similarity 0.90)
- Shift the Lens: Environment-Aware Unsupervised Camouflaged Object Detection (CVPR 2025 · similarity 0.90)
- Just a Hint: Point-Supervised Camouflaged Object Detection (ECCV 2024 · similarity 0.89)
- Camouflage-aware Image-Text Retrieval via Expert Collaboration (CVPR 2026 · similarity 0.89)
- UCOD-DPL: Unsupervised Camouflaged Object Detection via Dynamic Pseudo-label Learning (CVPR 2025 · similarity 0.87)
- SdalsNet: Self-Distilled Attention Localization and Shift Network for Unsupervised Camouflaged Object Detection (AAAI 2025 · similarity 0.87)
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.
