Summary of Do More Details Always Introduce More Hallucinations in Lvlm-based Image Captioning?, by Mingqian Feng et al.
Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?
by Mingqian Feng, Yunlong Tang, Zeliang Zhang, Chenliang Xu
First submitted to arxiv on: 18 Jun 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 abstract presents a research paper that investigates object hallucination (OH) in Large Vision-Language Models (LVLMs) used for image captioning. The authors argue that previous studies have incorrectly attributed OH to the inclusion of more details, instead identifying technical flaws in existing evaluation metrics as the true cause. This finding raises questions about the reliability of model evaluations and conclusions drawn regarding OH. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The research paper explores object hallucination (OH) in Large Vision-Language Models (LVLMs), which are used for image captioning tasks. The study reveals that previous methods to evaluate these models contain flaws, leading to inaccurate results and conclusions. This discovery has sparked debate on whether adding more details always increases the likelihood of OH. |
Keywords
» Artificial intelligence » Hallucination » Image captioning » Likelihood
