Research map / Architectures and efficiency / CNN design
Frequency-Domain Dynamic Pruning for Convolutional 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 |
|---|---|---|---|
| prune DCT frequency-domain coefficients instead of spatial weights (dynamic pruning) | LeNet-5 · MNIST | compression ratio: 108× -> 130× | Helped |
| prune DCT frequency-domain coefficients instead of spatial weights | AlexNet · ImageNet | compression ratio: 17.7× -> 20.9× | Helped |
| add band-adaptive compression rates per frequency band (ablation) | FDNP · MNIST | compression ratio: 130× -> 150× | Helped |
| add band-adaptive compression rates per frequency band (ablation) | FDNP · ImageNet | compression ratio: 20.9× -> 22.6× | Helped |
| add band-adaptive compression rates per frequency band (ablation) | FDNP · ImageNet | top-1 accuracy: 56.84% -> 56.82% | No clear effect |
| increase per-layer compression rate gamma (ablation) | FDNP/BA-FDNP · CIFAR-10 | accuracy | Hurt |
Closest papers by meaning
- CNNpack: Packing Convolutional Neural Networks in the Frequency Domain (NeurIPS 2016 · similarity 0.89)
- Interspace Pruning: Using Adaptive Filter Representations To Improve Training of Sparse CNNs (CVPR 2022 · similarity 0.89)
- Faster CNNs with Direct Sparse Convolutions and Guided Pruning (ICLR 2017 · similarity 0.88)
- Dynamic Structure Pruning for Compressing CNNs (AAAI 2023 · similarity 0.88)
- Frequency Domain Compact 3D Convolutional Neural Networks (CVPR 2020 · similarity 0.88)
- BilevelPruning: Unified Dynamic and Static Channel Pruning for Convolutional Neural Networks (CVPR 2024 · similarity 0.88)
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.