Summary of Adaneg: Adaptive Negative Proxy Guided Ood Detection with Vision-language Models, by Yabin Zhang and Lei Zhang
AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models
by Yabin Zhang, Lei Zhang
First submitted to arxiv on: 26 Oct 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 The proposed approach, titled AdaNeg, utilizes adaptive negative proxies to enhance the effectiveness of pre-trained vision-language models in identifying out-of-distribution (OOD) samples. By dynamically generating these proxies during testing using actual OOD images, the method aligns with the underlying label space, improving performance. The approach integrates static negative labels with adaptive proxies, leveraging textual and visual knowledge for enhanced results. AdaNeg is training-free, annotation-free, and maintains fast testing speed. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper introduces a new way to help pre-trained models understand when an image doesn’t belong. They use real images from the “wrong” category to create better labels that match what the model sees in new, unseen photos. This helps the model make fewer mistakes by combining text-based and visual information. The result is a more accurate approach called AdaNeg that can identify out-of-distribution images well. |
