Research map / Detection and segmentation / CNN features
Mamba Capsule Routing Towards Part-Whole Relational Camouflaged Object Detection
Dingwen Zhang, Liangbo Cheng, Yi Liu, Xinggang Wang, Junwei Han
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 mamba capsule generation (MCG) module (ablation) | Swin-T baseline · COD10K | MAE: 0.0292 -> 0.0269 | Improved |
| add mamba capsule generation (MCG) module (ablation) | Swin-T baseline · CAMO | F_m: 0.8250 -> 0.8338 | Improved |
| add capsules spatial details retrieval (CSDR) (ablation) | Baseline + MCG · CAMO | MAE: 0.0581 -> 0.0547 | Improved |
| add capsules spatial details retrieval (CSDR) (ablation) | Baseline + MCG · NC4K | S_m: 0.8710 -> 0.8751 | Improved |
| generate type-level capsules with Mamba instead of fully connected layer (ablation) | MCRNet · CAMO | MAE: 0.0581 -> 0.0547 | Improved |
| generate type-level capsules with Mamba instead of fully connected layer (ablation) | MCRNet · NC4K | E_m: 0.9216 -> 0.9301 | Improved |
| use 32 mamba capsules instead of 128 (ablation) | MCRNet · CAMO | MAE: 0.0575 -> 0.0547 | Improved |
| use 32 mamba capsules instead of 0 (ablation) | MCRNet · COD10K | F_m: 0.7921 -> 0.8069 | Improved |
| increase mamba capsules from 32 to 64 (ablation) | MCRNet · NC4K | F_m: 0.8570 -> 0.8592 | No clear effect |
| use four scanning directions instead of one (ablation) | MCRNet · CAMO | S_m: 0.8463 -> 0.8536 | Improved |
| use four scanning directions instead of two (ablation) | MCRNet · CAMO | MAE: 0.0561 -> 0.0547 | Improved |
| use mamba capsule routing instead of EM routing (ablation) | MCRNet · CAMO | MAE: 0.0623 -> 0.0547 | Improved |
Closest papers by meaning
- STAR-Caps: Capsule Networks with Straight-Through Attentive Routing (NeurIPS 2019 · similarity 0.85)
- Matrix capsules with EM routing (ICLR 2018 · similarity 0.84)
- OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning (CVPR 2024 · similarity 0.83)
- Mamba YOLO: A Simple Baseline for Object Detection with State Space Model (AAAI 2025 · similarity 0.83)
- MambaOut: Do We Really Need Mamba for Vision? (CVPR 2025 · similarity 0.83)
- Samba: A Unified Mamba-based Framework for General Salient Object Detection (CVPR 2025 · similarity 0.82)
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.
