Research map / Architectures and efficiency / CNN design
Convolutional Neural Network Pruning With Structural Redundancy Reduction
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 |
|---|---|---|---|
| prune filters from layers selected by graph redundancy | ResNet50 · ImageNet | Top-1 accuracy drop: 4.89% -> 0.37% | Helped |
| use graph redundancy instead of number of filters to measure layer redundancy (ablation) | SRR pruning on ResNet50 · ImageNet | Top-1 accuracy drop: 1.25% -> 0.37% | Helped |
| use graph redundancy instead of PCA to measure layer redundancy (ablation) | SRR pruning on ResNet50 · ImageNet | Top-1 accuracy drop: 0.94% -> 0.37% | Helped |
| randomly select filters within identified redundant layers rather than select by minimum weight (ablation) | SRR pruning · CIFAR-10 | accuracy: 75.99% -> 75.82% | No clear effect |
| use PCA rather than graph redundancy to identify redundant layers (ablation) | SRR pruning on ResNet50 · ImageNet | Top-1 accuracy drop: 0.37% -> 0.94% | Hurt |
| use number of filters rather than graph redundancy to identify redundant layers (ablation) | SRR pruning on ResNet50 · ImageNet | Top-1 accuracy drop: 0.37% -> 1.25% | Hurt |
Closest papers by meaning
- Rethinking the Pruning Criteria for Convolutional Neural Network (NeurIPS 2021 · similarity 0.93)
- Pruning from Scratch (AAAI 2020 · similarity 0.92)
- A Probabilistic Approach to Neural Network Pruning (ICML 2021 · similarity 0.92)
- RED : Looking for Redundancies for Data-FreeStructured Compression of Deep Neural Networks (NeurIPS 2021 · similarity 0.92)
- Dynamic Structure Pruning for Compressing CNNs (AAAI 2023 · similarity 0.91)
- Pruning Filters for Efficient ConvNets (ICLR 2017 · similarity 0.91)
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.