Research map / Architectures and efficiency / CNN design
Deep Texture Recognition via Exploiting Cross-Layer Statistical Self-Similarity
Check 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 |
|---|---|---|---|
| Add the CLASS module to ResNet18 (ablation) | ResNet18 · GTOS-Mobile | classification accuracy (%): 81.91 ± 1.5 -> 85.25 ± 1.3 | Helped |
| Add the CLASS module to ResNet18 (ablation) | ResNet18 · MINC-2500 | classification accuracy (%): 77.98 ± 0.5 -> 80.50 ± 0.6 | Helped |
| Use DBC-based SSS statistics instead of mean pooling for cross-layer statistics (ablation) | CLASSNet with ResNet18 · GTOS-Mobile | classification accuracy (%): 83.43 ± 2.0 -> 85.25 ± 1.3 | Helped |
| Use DBC-based SSS statistics instead of mean pooling for cross-layer statistics (ablation) | CLASSNet with ResNet18 · MINC-2500 | classification accuracy (%): 78.63 ± 0.4 -> 80.50 ± 0.6 | Helped |
Closest papers by meaning
- Deep TEN: Texture Encoding Network (CVPR 2017 · similarity 0.87)
- Deep Structure-Revealed Network for Texture Recognition (CVPR 2020 · similarity 0.87)
- Visualizing and Understanding Deep Texture Representations (CVPR 2016 · similarity 0.87)
- FASON: First and Second Order Information Fusion Network for Texture Recognition (CVPR 2017 · similarity 0.86)
- Chebyshev Attention Depth Permutation Texture Network with Latent Texture Attribute Loss (CVPR 2025 · similarity 0.85)
- ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression (NeurIPS 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.