Summary of Text-guided Attention Is All You Need For Zero-shot Robustness in Vision-language Models, by Lu Yu et al.
Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models
by Lu Yu, Haiyang Zhang, Changsheng Xu
First submitted to arxiv on: 29 Oct 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 new strategy, Text-Guided Attention for Zero-Shot Robustness (TGA-ZSR), to improve the robustness of pre-trained vision-language models like CLIP. The approach consists of two components: an Attention Refinement module and an Attention-based Model Constraint module. The goal is to maintain the generalization capabilities of the original model while enhancing its adversarial robustness. The paper demonstrates a 9.58% improvement in zero-shot robust accuracy over state-of-the-art techniques across 16 datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper makes pre-trained vision-language models more resistant to attacks by introducing a new strategy called Text-Guided Attention for Zero-Shot Robustness (TGA-ZSR). It uses two components to keep the model’s performance on clean data while making it more robust. The goal is to help the model work well even when given unexpected data. |
Keywords
» Artificial intelligence » Attention » Generalization » Zero shot
