Research map / Architectures and efficiency / CNN design
Learning Versatile Convolution Filters for Efficient Visual Recognition
Kai Han, Yunhe Wang, Chang Xu, Chunjing Xu, Enhua Wu, Dacheng Tao
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 |
|---|---|---|---|
| use separate instead of shared learnable masks (ablation) | L-Versatile (s=2) ResNet-56 · CIFAR-10 | accuracy: 92.8% -> 93.4% | Improved |
| use separate instead of shared learnable masks (ablation) | L-Versatile (s=4) ResNet-50 · ImageNet | top-1 error: 26.8% -> 25.5% | Improved |
| use separate instead of shared learnable masks (ablation) | L-Versatile (s=4) AlexNet · ImageNet | top-1 error: 43.7% -> 43.1% | Improved |
| set channel overlap and stride to 8 instead of 1 (ablation) | C-Versatile ResNet-56 · CIFAR-10 | accuracy: 92.4% -> 93.4% | Improved |
| increase channel overlap and stride from 8 to 12 (ablation) | C-Versatile ResNet-56 · CIFAR-10 | accuracy: 93.4% -> 92.4% | Hurt |
| reduce filters further with g=2 instead of g=8 at c-c_hat=8 (ablation) | C-Versatile ResNet-56 · CIFAR-10 | accuracy: 93.4% -> 91.2% | Hurt |
| add channel versatile filters to spatial versatile filters | S-Versatile ResNet-56 · CIFAR-10 | accuracy: 93.2% -> 92.1% | Hurt |
| increase s from 2 to 4 in separate L-Versatile (ablation) | ResNet-56 · CIFAR-10 | accuracy: 93.4% -> 92.8% | Hurt |
| increase s to 6 in separate L-Versatile (ablation) | ResNet-56 · CIFAR-10 | accuracy: 93.4% -> 92.4% | Hurt |
| use spatial versatile filters instead of vanilla filters | AlexNet · ImageNet | top-1 error: 42.9% -> 42.1% | Improved |
| use spatial versatile filters instead of vanilla filters | ResNet-50 · ImageNet | top-1 error: 24.7% -> 24.5% | Improved |
| increase s from 4 to 32 in separate L-Versatile (ablation) | ResNet-50 · ImageNet | top-5 error: 8.0% -> 8.7% | Hurt |
Closest papers by meaning
- Learning Versatile Filters for Efficient Convolutional Neural Networks (NeurIPS 2018 · similarity 0.96)
- CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters (CVPR 2022 · similarity 0.91)
- GFNet: Global Filter Networks for Visual Recognition (TPAMI 2023 · similarity 0.90)
- The Master Key Filters Hypothesis: Deep Filters Are General (AAAI 2025 · similarity 0.87)
- The Quest for Universal Master Key Filters in DS-CNNs (NeurIPS 2025 · similarity 0.87)
- PICNN: A Pathway towards Interpretable Convolutional Neural Networks (AAAI 2024 · 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.
