Research map / Detection and segmentation / Open-set and few-shot detection
Referring Camouflaged Object Detection
Xuying Zhang, Bowen Yin, Zheng Lin, Qibin Hou, Deng-Ping Fan, Ming‐Ming Cheng
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 referring images with salient objects (Ref-COD) to the FPN baseline | FPN COD baseline · R2C7K test (overall) | weighted F-measure: 0.604 -> 0.669 | Improved |
| add Referring Mask Generation module (ablation) | R2CNet · R2C7K test (overall) | weighted F-measure: 0.604 -> 0.661 | Improved |
| add Referring Feature Enrichment module (ablation) | R2CNet · R2C7K test (overall) | weighted F-measure: 0.604 -> 0.644 | Improved |
| combine RMG and RFE (ablation) | R2CNet · R2C7K test (overall) | weighted F-measure: 0.604 -> 0.669 | Improved |
| add reference branch to PFNet | PFNet · R2C7K test (overall) | S-measure: 0.791 -> 0.811 | Improved |
| add reference branch to BGNet | BGNet · R2C7K test (overall) | S-measure: 0.818 -> 0.840 | Improved |
| add reference branch to ZoomNext | ZoomNext · R2C7K test (overall) | S-measure: 0.838 -> 0.850 | Improved |
| add reference branch to DGNet | DGNet · R2C7K test (overall) | S-measure: 0.816 -> 0.821 | Improved |
| apply Ref design to SOD models | VSCode · CoSOD3K | S-measure: 0.861 -> 0.874 | Improved |
| apply Ref design to SOD models | VST++ · CoSOD3K | S-measure: 0.846 -> 0.858 | Improved |
| use affine transformation and ConvLSTM fusion in RMG instead of multiply and concat (ablation) | R2CNet · R2C7K test (overall) | weighted F-measure: 0.656 -> 0.669 | Improved |
| add cross-scale path in RFE (ablation) | R2CNet · R2C7K test (overall) | weighted F-measure: 0.665 -> 0.669 | 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.
- ZoomNext — ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection (TPAMI 2024) · better on 1 of 1 shared result
- ZoomNet — Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition (ECCV 2018) · 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 0.89)
- Segment, Magnify and Reiterate: Detecting Camouflaged Objects the Hard Way (CVPR 2022 · similarity 0.89)
- Just a Hint: Point-Supervised Camouflaged Object Detection (ECCV 2024 · similarity 0.88)
- Referring and Reasoning Camouflaged Object Segmentation in Audio-Visual Scenes (NeurIPS 2026 · similarity 0.88)
- SAM-COD: SAM-guided Unified Framework for Weakly-Supervised Camouflaged Object Detection (ECCV 2024 · similarity 0.88)
- Shift the Lens: Environment-Aware Unsupervised Camouflaged Object Detection (CVPR 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.
