Research map / Architectures and efficiency / Pruning and efficient tuning
OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization
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 |
|---|---|---|---|
| Use OPQ for one-shot pruning and quantization instead of CLIP-Q | AlexNet · ImageNet | compression rate: 138.96× vs 119.09× | Helped |
| Use OPQ for one-shot pruning and quantization instead of CLIP-Q | VGG-16 · ImageNet | Top-1 accuracy: 71.39 vs 69.2 | Helped |
| Use OPQ for one-shot pruning and quantization instead of CLIP-Q | MobileNet-V1 · ImageNet | Top-1 accuracy: +0.55% | Helped |
| Use OPQ for one-shot pruning and quantization instead of CLIP-Q | ResNet-50 · ImageNet | compression rate: 38.03× vs 31.81× | Helped |
Closest papers by meaning
- Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning (NeurIPS 2022 · similarity 0.92)
- Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-Based Approach (CVPR 2020 · similarity 0.91)
- CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization (CVPR 2018 · similarity 0.90)
- Focused Quantization for Sparse CNNs (NeurIPS 2019 · similarity 0.90)
- Effective Interplay between Sparsity and Quantization: From Theory to Practice (ICLR 2025 · similarity 0.89)
- Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression (CVPR 2025 · 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.