Summary of Mos: Model Surgery For Pre-trained Model-based Class-incremental Learning, by Hai-long Sun et al.
MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning
by Hai-Long Sun, Da-Wei Zhou, Hanbin Zhao, Le Gan, De-Chuan Zhan, Han-Jia Ye
First submitted to arxiv on: 12 Dec 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 proposed MOdel Surgery (MOS) addresses catastrophic forgetting in Class-Incremental Learning by introducing task-specific adapters and a training-free self-refined adapter retrieval mechanism. By continually adjusting the pre-trained model to downstream tasks, MOS mitigates parameter-level forgetting through an adapter merging approach that learns task-specific information. During inference, the self-refined retrieval mechanism leverages the model’s inherent ability for better adapter selection. Experimental results on seven benchmark datasets demonstrate MOS’s state-of-the-art performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary MOdel Surgery is a new way to help artificial intelligence models remember what they learned earlier when they’re learning something new. This problem is called “catastrophic forgetting.” To solve it, the researchers created special helpers for the model that allow it to adapt to new tasks without forgetting old ones. They also came up with a way to use the model’s own abilities to pick the right helper during testing. The results show that this approach works really well on many different datasets. |
Keywords
» Artificial intelligence » Inference
