Summary of Flatness Improves Backbone Generalisation in Few-shot Classification, by Rui Li et al.
Flatness Improves Backbone Generalisation in Few-shot Classification
by Rui Li, Martin Trapp, Marcus Klasson, Arno Solin
First submitted to arxiv on: 11 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
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 The paper proposes an effective strategy for few-shot classification (FSC) in multi-domain settings by leveraging pre-trained backbones and adapting to new classes with few examples. The approach involves flatness-aware training and fine-tuning, which is theoretically grounded and empirically performs on par or better than state-of-the-art methods. The work highlights the importance of backbone training for good generalization across different adaptation methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper helps solve a big problem in using deep neural networks in real-world situations by allowing them to learn new tasks quickly, even with only a few examples. It does this by using pre-trained models and adapting them to new classes. The approach is simpler than existing solutions but performs just as well or better. |
Keywords
» Artificial intelligence » Classification » Few shot » Fine tuning » Generalization
