Research map / Detection and segmentation / CNN features
Inferring Camouflaged Objects by Texture-Aware Interactive Guidance Network
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use Texture labels instead of ConEdge labels with Structure 1 (ablation) | TINet · CAMO | Fβw: .668 -> .678 | Helped |
| Use Texture labels instead of ConEdge labels with Structure 1 (ablation) | TINet · CHAMELEON | Fβw: .774 -> .783 | Helped |
| Use Structure 1 instead of Structure 2 with Texture labels (ablation) | TINet · CAMO | Fβw: .668 -> .678 | Helped |
| Use Structure 2 instead of Structure 1 with ConEdge labels (ablation) | TINet · DUT-OMRON | Fβw: .748 -> .754 | Helped |
| Add one-way texture-to-segmentation guidance (ablation) | TINet on COD · CHAMELEON | Fβw: .760 -> .764 | Helped |
| Add bidirectional guidance between texture and segmentation features (ablation) | TINet on COD · CHAMELEON | Fβw: .764 -> .772 | Helped |
| Add bidirectional guidance between edge and segmentation features (ablation) | TINet on SOD · DUTS-Test | Fβw: .830 -> .834 | Helped |
| Add the boundary weight map to the loss (ablation) | TINet on COD · CHAMELEON | Fβw: .772 -> .783 | Helped |
| Add the boundary weight map to the loss (ablation) | TINet on SOD · DUTS-Test | Fβw: .834 -> .842 | Helped |
| Use the FGD result instead of the output at the ILS supervision position (ablation) | TINet on COD · CHAMELEON | Fβw: .775 -> .783 | Helped |
| Replace concatenation with multiplication in FGM-T (ablation) | TINet on COD · CHAMELEON | Fβw: .783 -> .773 | Hurt |
| Remove same-type feature guidance (ablation) | TINet on COD · CHAMELEON | Fβw: .783 -> .767 | Hurt |
Closest papers by meaning
- EReCu: Pseudo-label Evolution Fusion and Refinement with Multi-Cue Learning for Unsupervised Camouflage Detection (CVPR 2026 · similarity 0.88)
- Zoom in and Out: A Mixed-Scale Triplet Network for Camouflaged Object Detection (CVPR 2022 · similarity 0.88)
- High-Resolution Iterative Feedback Network for Camouflaged Object Detection (AAAI 2023 · similarity 0.88)
- Camouflage Anything: Learning to Hide using Controlled Out-painting and Representation Engineering (CVPR 2025 · similarity 0.86)
- Shift the Lens: Environment-Aware Unsupervised Camouflaged Object Detection (CVPR 2025 · similarity 0.85)
- SdalsNet: Self-Distilled Attention Localization and Shift Network for Unsupervised Camouflaged Object Detection (AAAI 2025 · similarity 0.84)
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.