Research map / Detection and segmentation / CNN features
Improving SAM for Camouflaged Object Detection via Dual Stream Adapters
Jiaming Liu, Linghe Kong, Guihai Chen
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 dual stream adapter to SAM baseline (ablation) | SAM-COD · COD10K | S_m: .829 -> .865 | Improved |
| add bidirectional knowledge distillation (ablation) | SAM-COD · COD10K | S_m: .865 -> .870 | Improved |
| add mixed prompt embedding (ablation) | SAM-COD · COD10K | S_m: .870 -> .887 | Improved |
| use wavelet-filtered adapter instead of LoRA-style adapter (ablation) | SAM-COD · COD10K | S_m: .848 -> .887 | Improved |
| add discrete wavelet transform to adapter (ablation) | SAM-COD · COD10K | S_m: .868 -> .887 | Improved |
| add depth stream (dual-stream adapter) to RGB-only (ablation) | SAM-COD · COD10K | S_m: .881 -> .887 | Improved |
| use both model and modal distillation instead of a single one (ablation) | SAM-COD · COD10K | S_m: .875 -> .887 | Improved |
| order distillation PVT->RGB->Depth instead of PVT->Depth->RGB (ablation) | SAM-COD · COD10K | S_m: .880 -> .887 | Improved |
| include PVT embedding in mixed prompt embedding (ablation) | SAM-COD · COD10K | S_m: .873 -> .887 | Improved |
| SAM-COD (RGB) versus SAM-Adapter on COD10K structure measure | RGB-only setting · COD10K | S_m: .883 -> .881 | Hurt |
| SAM-COD versus PopNet on CHAMELEON | RGB-D setting · CHAMELEON | S_m: .910 -> .893 | Hurt |
Closest papers by meaning
- SAM-COD: SAM-guided Unified Framework for Weakly-Supervised Camouflaged Object Detection (ECCV 2024 · similarity 0.89)
- SAM-DAQ: Segment Anything Model with Depth-guided Adaptive Queries for RGB-D Video Salient Object Detection (AAAI 2026 · similarity 0.89)
- Enhancing Prompt Generation with Adaptive Refinement for Camouflaged Object Detection (ICCV 2025 · similarity 0.89)
- EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything (CVPR 2024 · similarity 0.88)
- Endow SAM with Keen Eyes: Temporal-spatial Prompt Learning for Video Camouflaged Object Detection (CVPR 2024 · similarity 0.88)
- CamSAM2: Segment Anything Accurately in Camouflaged Videos (NeurIPS 2025 · similarity 0.86)
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.
