Summary of Out-of-distribution Detection with Overlap Index, by Hao Fu et al.
Out-of-Distribution Detection with Overlap Index
by Hao Fu, Prashanth Krishnamurthy, Siddharth Garg, Farshad Khorrami
First submitted to arxiv on: 9 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Machine Learning (stat.ML)
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 a novel out-of-distribution (OOD) detection approach that employs an overlap index (OI)-based confidence score function. This non-parametric, lightweight, and interpretable method evaluates the likelihood of a given input belonging to the same distribution as available in-distribution (ID) samples. The proposed OI-based OOD detector is competitive with state-of-the-art detectors in terms of detection accuracy on various datasets while requiring less computational resources. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about finding out when something doesn’t fit into what we know. This is important because we can’t just use machines that learn to do things without checking if they are making sense or not. The current ways of doing this have some problems, like being slow or needing a lot of adjusting. So, the researchers came up with a new way using something called an overlap index (OI). It’s easy to understand and doesn’t require a lot of computer power. They tested it on many different datasets and found that it worked just as well as other methods, but was faster and used less memory. |
Keywords
» Artificial intelligence » Likelihood
