Research map / Architectures and efficiency / CNN design
Orthogonal Convolutional Neural Networks
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 |
|---|---|---|---|
| Replace SRIP with OCNN convolutional orthogonality | ResNet34 · ResNet34 evaluation | Top-1 error: 26.10 -> 25.87 | Helped |
| Replace SRIP with OCNN convolutional orthogonality | ResNet34 · ResNet34 evaluation | Top-5 error: 8.32 -> 7.89 | Helped |
| Add OCNN regularization to ProxyNCA | ProxyNCA · CARS 196 | NMI: 62.4 -> 63.6 | Helped |
| Add OCNN regularization to ProxyNCA | ProxyNCA · CARS 196 | F1: 29.2 -> 30.2 | Helped |
| Add OCNN regularization to ProxyNCA | ProxyNCA · CARS 196 | Recall@1: 67.9 -> 68.8 | Helped |
| Add OCNN regularization to ProxyNCA | ProxyNCA · CARS 196 | Recall@2: 78.2 -> 79.0 | Helped |
| Add OCNN regularization to ProxyNCA | ProxyNCA · CARS 196 | Recall@4: 85.6 -> 87.4 | Helped |
| Add OCNN regularization to ProxyNCA | ProxyNCA · CARS 196 | Recall@8: 90.6 -> 92.0 | Helped |
| Use OCNN instead of kernel orthogonality | ResNet34 · ResNet34 evaluation | Top-1 error: 26.68 -> 25.87 | Helped |
| Use OCNN instead of kernel orthogonality | ResNet34 · ResNet34 evaluation | Top-5 error: 8.43 -> 7.89 | Helped |
| Use OCNN instead of kernel orthogonality | ProxyNCA · CARS 196 | NMI: 63.1 -> 63.6 | Helped |
Closest papers by meaning
- Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework (ICML 2022 · similarity 0.92)
- An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures (ICML 2025 · similarity 0.90)
- Constructing Orthogonal Convolutions in an Explicit Manner (ICLR 2022 · similarity 0.90)
- Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks (ICML 2023 · similarity 0.89)
- Towards an Effective Orthogonal Dictionary Convolution Strategy (AAAI 2022 · similarity 0.87)
- Skew Orthogonal Convolutions (ICML 2021 · similarity 0.87)
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.