Research map / Architectures and efficiency / Pruning and efficient tuning
Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration
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 |
|---|---|---|---|
| learn a different pruning criterion for each layer | ResNet-50 · ImageNet-1k | top-5 accuracy: 91.20 -> 92.04 | Helped |
| learn layer-specific pruning criteria | ResNet-56 · CIFAR-100 | accuracy: 69.66 -> 70.83 | Helped |
| learn layer-specific pruning criteria | ResNet-110 · CIFAR-10 | FLOPs reduction: 38.6 -> 60.3 | Helped |
| include adversarial ℓ1-norm and adversarial ℓ2-norm criteria in the candidate set (ablation) | LFPC on ResNet-56 · CIFAR-10 | accuracy: 93.45 (±0.13) -> 93.09 (±0.09) | Mixed |
| use a cosine rather than step scheduler for retraining (ablation) | LFPC on ResNet-56 · CIFAR-10 | accuracy: 93.54(±0.16) -> 93.56(±0.15) | No clear effect |
Closest papers by meaning
- Rethinking the Pruning Criteria for Convolutional Neural Network (NeurIPS 2021 · similarity 0.92)
- Pruning Filters for Efficient ConvNets (ICLR 2017 · similarity 0.92)
- DPFPS: Dynamic and Progressive Filter Pruning for Compressing Convolutional Neural Networks from Scratch (AAAI 2021 · similarity 0.92)
- Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks (NeurIPS 2019 · similarity 0.91)
- Provable Filter Pruning for Efficient Neural Networks (ICLR 2020 · 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.