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
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 Intra-SPQ (ablation) | USCNet ARM · USC12K overall scenes | mIoU: 75.31 -> 78.03 | Improved |
| add Inter-SPQ (ablation) | USCNet ARM · USC12K overall scenes | mIoU: 76.96 -> 78.03 | Improved |
| add Intra-SPQ (ablation) | USCNet ARM · USC12K overall scenes | CSCS: 9.07 -> 7.49 | Improved |
| add Q2I and I2Q attention (ablation) | USCNet ARM · USC12K overall scenes | mIoU: 74.77 -> 78.03 | Improved |
| add Q2I and I2Q attention (ablation) | USCNet ARM · USC12K overall scenes | CSCS: 9.85 -> 7.49 | Improved |
| add I2Q attention (ablation) | USCNet ARM · USC12K overall scenes | CSCS: 8.52 -> 7.49 | Improved |
| add ARM with frozen mask decoder to SAM2-Adapter (ablation) | USCNet · USC12K overall scenes | mIoU: 74.98 -> 78.03 | Improved |
| tune the encoder with adapters instead of freezing it (ablation) | SAM2 baseline · USC12K overall scenes | mIoU: 68.78 -> 74.98 | Improved |
| train SOD model ICON on USC12K | ICON on COD datasets · COD10K | weighted F-measure false detection: 0.6384 -> 0.0146 | Improved |
| train COD model SINet-V2 on USC12K | SINet-V2 on SOD datasets · DUTS | weighted F-measure false detection: 0.7412 -> 0.0708 | Improved |
| train unified VSCode on USC12K with COD prompt | VSCode on SOD datasets · HKU-IS | weighted F-measure false detection: 0.8733 -> 0.0391 | Improved |
| use USCNet instead of VSCode | unified model generalization · NC4K | F_beta max: .626 -> .794 | Improved |
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.
- CamoDiffusion — CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Models (AAAI 2024) · 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
- Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground (ECCV 2018 · similarity 0.92)
- Uncertainty-Aware Joint Salient Object and Camouflaged Object Detection (CVPR 2021 · similarity 0.92)
- Camouflaged Object Detection (CVPR 2020 · similarity 0.91)
- Salient Objects in Clutter (TPAMI 2022 · similarity 0.91)
- 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 0.90)
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.
