Research map / Architectures and efficiency / CNN design
Provable Filter Pruning for Efficient Neural Networks
Read the paperCheck 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 |
|---|---|---|---|
| Use sensitivity-based filter sampling instead of SoftNet | LeNet-300-100 · MNIST | PR (%): 81.69 -> 84.32 | Helped |
| Use sensitivity-based filter sampling instead of FT | LeNet-5 · MNIST | PR (%): 85.04 -> 92.37 | Helped |
| Use sensitivity-based filter sampling instead of SoftNet | ResNet20 · CIFAR-10 | PR (%): 46.42 -> 62.67 | Helped |
| Use sensitivity-based filter sampling instead of FT | ResNet56 · CIFAR-10 | PR (%): 81.46 -> 88.98 | Helped |
| Use sensitivity-based filter sampling instead of FT | ResNet110 · CIFAR-10 | PR (%): 86.38 -> 92.07 | Helped |
| Use sensitivity-based filter sampling instead of FT | VGG16 · CIFAR-10 | PR (%): 80.09 -> 94.32 | Helped |
| Use sensitivity-based filter sampling instead of ThiNet | DenseNet22 · CIFAR-10 | PR (%): 50.76 -> 56.44 | Helped |
| Use sensitivity-based filter sampling instead of FT | WRN16-8 · CIFAR-10 | PR (%): 24.88 -> 66.22 | Helped |
| Use sensitivity-based sampling instead of SoftNet | ResNet20 · CIFAR-10 | FR (%): 49.40 -> 45.46 | Hurt |
Closest papers by meaning
- RePr: Improved Training of Convolutional Filters (CVPR 2019 · similarity 0.93)
- Pruning Filters for Efficient ConvNets (ICLR 2017 · similarity 0.92)
- A Probabilistic Approach to Neural Network Pruning (ICML 2021 · similarity 0.91)
- Auto-Balanced Filter Pruning for Efficient Convolutional Neural Networks (AAAI 2018 · similarity 0.91)
- DPFPS: Dynamic and Progressive Filter Pruning for Compressing Convolutional Neural Networks from Scratch (AAAI 2021 · similarity 0.91)
- Entropy Induced Pruning Framework for Convolutional Neural Networks (AAAI 2024 · similarity 0.90)
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.