Summary of Separate, Dynamic and Differentiable (smart) Pruner For Block/output Channel Pruning on Computer Vision Tasks, by Guanhua Ding et al.
Separate, Dynamic and Differentiable (SMART) Pruner for Block/Output Channel Pruning on Computer Vision Tasks
by Guanhua Ding, Zexi Ye, Zhen Zhong, Gang Li, David Shao
First submitted to arxiv on: 29 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel algorithm called SMART (Separate, Dynamic, and Differentiable) pruning is introduced to address the gap in existing block pruning methods. SMART leverages both weight and activation information to enhance accuracy, uses a differentiable top-k operator for precise control of resource constraints, and offers convergence guarantees under mild conditions. The algorithm satisfies three key requirements: maintaining high accuracy across diverse models and tasks, providing precise control over resource constraints, and offering convergence guarantees. Experiments involving seven models, four datasets, three computer vision tasks, and three block types demonstrate that SMART pruning achieves state-of-the-art performance in block pruning. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Block pruning is a way to make neural networks smaller and more efficient. A new algorithm called SMART helps achieve this by keeping accuracy high, controlling how much memory is used, and making sure the network doesn’t get stuck in a bad state. This algorithm works well across different models, tasks, and devices. It’s an important step forward for using neural networks on things like cameras and self-driving cars. |
Keywords
» Artificial intelligence » Pruning
