What's in the Image? A Deep-Dive into the Vision of Vision Language Models
Kaduri, Omri, Bagon, Shai, Dekel, Tali
–arXiv.org Artificial Intelligence
Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in comprehending complex visual content. However, the mechanisms underlying how VLMs process visual information remain largely unexplored. In this paper, we conduct a thorough empirical analysis, focusing on attention modules across layers. We reveal several key insights about how these models process visual data: (i) the internal representation of the query tokens (e.g., representations of "describe the image"), is utilized by VLMs to store global image information; we demonstrate that these models generate surprisingly descriptive responses solely from these tokens, without direct access to image tokens. (ii) Cross-modal information flow is predominantly influenced by the middle layers (approximately 25% of all layers), while early and late layers contribute only marginally.(iii) Fine-grained visual attributes and object details are directly extracted from image tokens in a spatially localized manner, i.e., the generated tokens associated with a specific object or attribute attend strongly to their corresponding regions in the image. We propose novel quantitative evaluation to validate our observations, leveraging real-world complex visual scenes. Finally, we demonstrate the potential of our findings in facilitating efficient visual processing in state-of-the-art VLMs.
arXiv.org Artificial Intelligence
Nov-26-2024
- Country:
- Europe > Switzerland
- North America > United States (0.67)
- Genre:
- Research Report > New Finding (0.87)
- Industry:
- Government
- Leisure & Entertainment > Sports (0.46)
- Transportation > Air (0.46)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning
- Neural Networks (0.67)
- Performance Analysis > Accuracy (1.00)
- Natural Language > Large Language Model (0.98)
- Vision (1.00)
- Machine Learning
- Information Technology > Artificial Intelligence