Summary of Out-of-distribution Detection Through Soft Clustering with Non-negative Kernel Regression, by Aryan Gulati et al.
Out-of-Distribution Detection through Soft Clustering with Non-Negative Kernel Regression
by Aryan Gulati, Xingjian Dong, Carlos Hurtado, Sarath Shekkizhar, Swabha Swayamdipta, Antonio Ortega
First submitted to arxiv on: 18 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 proposes a novel soft clustering approach for out-of-distribution (OOD) instance detection, which significantly reduces computational and storage complexities compared to existing methods. The proposed algorithm is based on non-negative kernel regression and achieves up to 11x improvement in inference time and 87% reduction in storage requirements while maintaining competitive performance on four benchmarks. Additionally, an entropy-constrained version of the algorithm is introduced, leading to further reductions in storage requirements (up to 97% lower than comparable approaches) while retaining performance. This soft clustering approach has potential for detecting tail-end phenomena in extreme-scale data settings. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about finding and identifying things that don’t belong to a specific group or category. The problem with current methods is that they use too much computer power and storage space. The new approach uses “soft clustering” which makes it faster and more efficient, using up to 11 times less computer time and reducing storage needs by up to 87%. This method works well on four different tests and could be used for large amounts of data. |
Keywords
» Artificial intelligence » Clustering » Inference » Regression
