Research map / Architectures and efficiency / Pruning and efficient tuning
Variational Convolutional Neural Network Pruning
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 |
|---|---|---|---|
| Use variational pruning instead of no pruning | VGG-16 · CIFAR-10 | accuracy: 93.25% -> 93.18% | No clear effect |
| Use variational pruning instead of no pruning | DenseNet-40 · CIFAR-10 | accuracy: 94.11% -> 93.16% | Hurt |
| Use variational pruning instead of no pruning | ResNet-164 · CIFAR-10 | accuracy: 93.58% -> 93.16% | No clear effect |
| Use variational pruning instead of no pruning | VGG-16 · CIFAR-100 | accuracy: 73.26% -> 73.33% | No clear effect |
| Use variational pruning instead of no pruning | DenseNet-40 · CIFAR-100 | accuracy: 74.64% -> 72.19% | Hurt |
| Use variational pruning instead of no pruning | ResNet-164 · CIFAR-100 | accuracy: 75.56% -> 73.76% | Hurt |
| Use variational pruning instead of no pruning | ResNet-50 · ImageNet validation | Top-1 accuracy: 75.1% -> 75.2% | Helped |
| Use variational pruning instead of no pruning | ResNet-50 · ImageNet validation | Top-5 accuracy: 92.8% -> 92.1% | Hurt |
| Replace deterministic scale-factor pruning with variational distribution-based pruning | DenseNet-40 · CIFAR-10 | accuracy: 89.5% -> 93.1% | Helped |
| Replace deterministic scale-factor pruning with variational distribution-based pruning | ResNet-164 · CIFAR-10 | accuracy: 47.7% -> 93.1% | Helped |
| Replace deterministic scale-factor pruning with variational distribution-based pruning | DenseNet-40 · CIFAR-100 | accuracy: 67.7% -> 72.1% | Helped |
| Replace deterministic scale-factor pruning with variational distribution-based pruning | ResNet-164 · CIFAR-100 | accuracy: 48.0% -> 73.7% | Helped |
Closest papers by meaning
- Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers (ICLR 2018 · similarity 0.92)
- Discrimination-aware Channel Pruning for Deep Neural Networks (NeurIPS 2018 · similarity 0.88)
- CHEX: CHannel EXploration for CNN Model Compression (CVPR 2022 · similarity 0.88)
- BilevelPruning: Unified Dynamic and Static Channel Pruning for Convolutional Neural Networks (CVPR 2024 · similarity 0.88)
- UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer (AAAI 2024 · similarity 0.86)
- REPrune: Channel Pruning via Kernel Representative Selection (AAAI 2024 · similarity 0.85)
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.