Learning to Look: A Foundation for Visual Understanding

Vision-language models (VLMs) suffer from visual hallucination, such as saying an object that is not present in an image. We ask a more fundamental question: whether a VLM is even aware of where it is looking before understanding the semantic meaning in the image. We formulate this question as a task: identifying which parts of its visual input were available to the model. We construct the task in a self-supervised way without manually labeling the available region to the model. Our experiments show that existing VLMs fail to localize the visible region. We further show that fine-tuning VLMs on the proposed task improves a model's awareness of visual input.