Summary of Selex: Self-expertise in Fine-grained Generalized Category Discovery, by Sarah Rastegar et al.
SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery
by Sarah Rastegar, Mohammadreza Salehi, Yuki M. Asano, Hazel Doughty, Cees G. M. Snoek
First submitted to arxiv on: 26 Aug 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); 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 This paper addresses the challenge of Generalized Category Discovery, aiming to simultaneously uncover novel categories and accurately classify known ones. Traditional methods often fall short in distinguishing between fine-grained categories. To overcome this limitation, the authors introduce a novel concept called self-expertise, which enhances the model’s ability to recognize subtle differences and uncover unknown categories. The approach combines unsupervised and supervised self-expertise strategies to refine the model’s discernment and generalization. Hierarchical pseudo-labeling is initially used to provide soft supervision, improving the effectiveness of self-expertise. The paper’s empirical results show that this method outperforms existing state-of-the-art techniques in Generalized Category Discovery across several fine-grained datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps machines learn to discover new categories and correctly group things into those categories. Right now, most methods don’t do a great job of telling apart very small differences between categories. To fix this, the authors came up with something called self-expertise, which makes the model better at noticing tiny differences and finding new categories. They use two ways to make this work: one that gets help from humans and another that doesn’t. By trying out these ideas on lots of datasets, they showed that their approach does a better job than other methods. |
Keywords
» Artificial intelligence » Generalization » Supervised » Unsupervised
