Summary of Compositional Entailment Learning For Hyperbolic Vision-language Models, by Avik Pal et al.
Compositional Entailment Learning for Hyperbolic Vision-Language Models
by Avik Pal, Max van Spengler, Guido Maria D’Amely di Melendugno, Alessandro Flaborea, Fabio Galasso, Pascal Mettes
First submitted to arxiv on: 9 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 paper proposes a novel approach to vision-language representation learning by leveraging the hierarchical nature of hyperbolic embeddings. The authors introduce Compositional Entailment Learning (CEL) for hyperbolic vision-language models, which organizes images, image boxes, and their textual descriptions through contrastive and entailment-based objectives. The CEL approach outperforms conventional Euclidean CLIP learning, as well as recent hyperbolic alternatives, with better zero-shot and retrieval generalization and stronger hierarchical performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper shows how to use the relationship between images and text to learn better representations of both visual and textual concepts. It does this by looking at each image not just as a single thing, but as a combination of smaller objects or “image boxes” that can be described with their own text. The authors use this information to train a model that can understand the hierarchical structure of images and text. |
Keywords
» Artificial intelligence » Generalization » Representation learning » Zero shot
