Research map / Architectures and efficiency / CNN design
Multi-Dimensional Pruning: A Unified Framework for Model Compression
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 |
|---|---|---|---|
| jointly prune spatial and channel dimensions | MDP on VGGNet · CIFAR-10 | Top-1 accuracy (%): 94.57 vs 94.57; 24.84 vs 34.97 #FLOPs (%) | Helped |
| jointly prune spatial and channel dimensions | MDP on ResNet-56 · CIFAR-10 | Top-1 accuracy (%): 94.29 vs 93.49 | Helped |
| jointly prune spatial and channel dimensions | MDP on MobileNet-V2 · CIFAR-10 | Top-1 accuracy (%): 95.14 vs 94.69 | Helped |
| jointly prune multiple dimensions rather than channel pruning followed by spatial pruning | ResNet-50 · ImageNet | Top-5 accuracy (%): 92.66 vs 92.46 | Helped |
| jointly prune spatial-temporal and channel dimensions | MDP on C3D · UCF-101 Split 1 | Video-level accuracy (%): 80.17 vs 77.77 | Helped |
| jointly prune spatial-temporal and channel dimensions | MDP on I3D · UCF-101 Split 1 | Video-level accuracy (%): 88.03 vs 85.38 | Helped |
| jointly prune spatial-temporal and channel dimensions | MDP on C3D · HMDB51 Split 1 | Video-level accuracy (%): 44.97 vs 43.53 | Helped |
| jointly prune spatial-temporal and channel dimensions | MDP on I3D · HMDB51 Split 1 | Video-level accuracy (%): 62.88 vs 57.84 | Helped |
| add channel pruning (ablation) | MDP on ResNet-56 · CIFAR-10 | accuracy (%): 93.39 -> 94.29 | Helped |
| add spatial pruning (ablation) | MDP on ResNet-56 · CIFAR-10 | accuracy (%): 92.86 -> 94.29 | Helped |
| add channel pruning (ablation) | MDP on C3D · UCF-101 | Video-level accuracy (%): 77.66 -> 80.17 | Helped |
| add spatial-temporal pruning (ablation) | MDP on C3D · UCF-101 | Video-level accuracy (%): 76.92 -> 80.17 | Helped |
Closest papers by meaning
- Towards Compact CNNs via Collaborative Compression (CVPR 2021 · similarity 0.91)
- Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework (ICML 2021 · similarity 0.90)
- MDP: Multidimensional Vision Model Pruning with Latency Constraint (CVPR 2025 · similarity 0.89)
- SPDY: Accurate Pruning with Speedup Guarantees (ICML 2022 · similarity 0.89)
- Convolutional Neural Network Pruning With Structural Redundancy Reduction (CVPR 2021 · similarity 0.89)
- Auto-Balanced Filter Pruning for Efficient Convolutional Neural Networks (AAAI 2018 · similarity 0.89)
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.