LE-CapsNet: A Light and Enhanced Capsule Network
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908654334115840 |
|---|---|
| author | Shiri, Pouya Baniasadi, Amirali |
| author_facet | Shiri, Pouya Baniasadi, Amirali |
| contents | Capsule Network (CapsNet) classifier has several advantages over CNNs, including better detection of images containing overlapping categories and higher accuracy on transformed images. Despite the advantages, CapsNet is slow due to its different structure. In addition, CapsNet is resource-hungry, includes many parameters and lags in accuracy compared to CNNs. In this work, we propose LE-CapsNet as a light, enhanced and more accurate variant of CapsNet. Using 3.8M weights, LECapsNet obtains 76.73% accuracy on the CIFAR-10 dataset while performing inference 4x faster than CapsNet. In addition, our proposed network is more robust at detecting images with affine transformations compared to CapsNet. We achieve 94.3% accuracy on the AffNIST dataset (compared to CapsNet 90.52%). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11708 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LE-CapsNet: A Light and Enhanced Capsule Network Shiri, Pouya Baniasadi, Amirali Computer Vision and Pattern Recognition Capsule Network (CapsNet) classifier has several advantages over CNNs, including better detection of images containing overlapping categories and higher accuracy on transformed images. Despite the advantages, CapsNet is slow due to its different structure. In addition, CapsNet is resource-hungry, includes many parameters and lags in accuracy compared to CNNs. In this work, we propose LE-CapsNet as a light, enhanced and more accurate variant of CapsNet. Using 3.8M weights, LECapsNet obtains 76.73% accuracy on the CIFAR-10 dataset while performing inference 4x faster than CapsNet. In addition, our proposed network is more robust at detecting images with affine transformations compared to CapsNet. We achieve 94.3% accuracy on the AffNIST dataset (compared to CapsNet 90.52%). |
| title | LE-CapsNet: A Light and Enhanced Capsule Network |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.11708 |