Research map / Architectures and efficiency / CNN design
MSPCaps: A Multi-Scale Patchify Capsule Network with Cross-Agreement Routing for Visual Recognition
Yudong Hu, Yueju Han, Rui Sun, Jinke Ren
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 multi-scale capsules (all three scales) instead of 8x8 only (ablation) | MSPCaps-T · CIFAR-10 | accuracy (%): 87.48 -> 88.71 | Improved |
| add 8x8 coarse scale to 32x32 and 16x16 scales (ablation) | MSPCaps-T · CIFAR-10 | accuracy (%): 81.57 -> 88.71 | Improved |
| add fine 32x32 scale to the 8x8 scale (with 16x16) (ablation) | MSPCaps-T · CIFAR-10 | accuracy (%): 87.48 -> 88.71 | Improved |
| use 2 cross-agreement routing blocks instead of 4 dynamic routing blocks (ablation) | MSPCaps-T · CIFAR-10 | accuracy (%): 87.46 -> 88.71 | Improved |
| use 2 cross-agreement routing blocks instead of 4 dynamic routing blocks (ablation) | MSPCaps-L · CIFAR-10 | accuracy (%): 92.56 -> 92.88 | Improved |
| share transformation weights within CAR (ablation) | MSPCaps-T · CIFAR-10 | accuracy (%): 87.59 -> 88.71 | Improved |
| share transformation weights within CAR (ablation) | MSPCaps-L · CIFAR-10 | accuracy (%): 92.88 -> 92.50 | Hurt |
| patch size 4 instead of 3 (ablation) | MSPCaps-T · CIFAR-10 | accuracy (%): 86.34 -> 88.71 | Improved |
| patch size 4 instead of 2 (ablation) | MSPCaps-T · CIFAR-10 | accuracy (%): 88.01 -> 88.71 | Improved |
| patch size 3 instead of 4 (ablation) | MSPCaps-L · CIFAR-10 | accuracy (%): 92.88 -> 93.30 | Improved |
| patch size 2 instead of 4 (ablation) | MSPCaps-L · CIFAR-10 | accuracy (%): 92.88 -> 93.16 (10.9M -> 39.4M params) | Mixed |
| smaller model (MSPCaps-T) under adversarial attack versus CapsNet | MSPCaps-T · CIFAR-10 FGSM/BIM | accuracy | Hurt |
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.
- DeepCaps — DeepCaps: Going Deeper With Capsule Networks (CVPR 2019) · 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
- STAR-Caps: Capsule Networks with Straight-Through Attentive Routing (NeurIPS 2019 · similarity 0.88)
- PT-CapsNet: A Novel Prediction-Tuning Capsule Network Suitable for Deeper Architectures (ICCV 2021 · similarity 0.87)
- Deep Layer Aggregation (CVPR 2018 · similarity 0.87)
- SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks (AAAI 2025 · similarity 0.84)
- OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning (CVPR 2024 · similarity 0.84)
- ParseCaps: An Interpretable Parsing Capsule Network for Medical Image Diagnosis (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.
