Summary of Negative Label Guided Ood Detection with Pretrained Vision-language Models, by Xue Jiang et al.
Negative Label Guided OOD Detection with Pretrained Vision-Language Models
by Xue Jiang, Feng Liu, Zhen Fang, Hong Chen, Tongliang Liu, Feng Zheng, Bo Han
First submitted to arxiv on: 29 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: 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 proposes a novel post-hoc out-of-distribution (OOD) detection method, NegLabel, which leverages negative labels from extensive corpus databases. The approach combines the OOD score with negative labels to achieve state-of-the-art performance on various benchmarks and generalizes well across multiple vision-language model (VLM) architectures. Theoretical analysis provides insight into the mechanism of negative labels. Extensive experiments demonstrate the method’s robustness against diverse domain shifts. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a new way to detect when data doesn’t belong in a group. It’s important because sometimes machines make mistakes on things they’ve never seen before. The team developed a method called NegLabel that uses lots of examples from large databases where the labels are wrong. They combined these incorrect labels with a score to figure out if something is out-of-distribution. Tests showed that NegLabel works really well and can handle different kinds of changes in data. |
Keywords
* Artificial intelligence * Language model
