3 accepted papers
Visually-grounded language models (VLMs) are highly effective in linking visual and textual information, yet they often struggle with basic classification and localization tasks. While classification mechanisms have been studied more extensively, the processes that support object localization remain
Humans acquire semantic object representations from egocentric visual streams with minimal supervision. Importantly, the visual system processes with high resolution only the center of its field of view and learns similar representations for visual inputs occurring close in time. This emphasizes slo…
Despite the growing use of transformer models in computer vision, a mechanistic understanding of these networks is still needed. This work introduces a method to reverse-engineer Vision Transformers trained to solve image classification tasks. Inspired by previous research in NLP, we demonstrate how…