VLM's Eye Examination: Instruct and Inspect Visual Competency of Vision Language Models

TL;DR

This paper introduces an eye examination process and dataset to evaluate how vision language models perceive visual elements, revealing their sensitivities and insensitivities to color, shape, and semantics, which can guide future improvements.

Contribution

It proposes a novel eye examination methodology and dataset to analyze VLMs' visual perception, providing insights into their sensitivities and limitations.

Findings

VLMs show varying sensitivity to different colors.

VLMs are consistently insensitive to green.

Shape sensitivity and semantic recognition vary with model capacity.

Abstract

Vision language models (VLMs) have shown promising reasoning capabilities across various benchmarks; however, our understanding of their visual perception remains limited. In this work, we propose an eye examination process to investigate how a VLM perceives images, specifically focusing on key elements of visual recognition, from primitive color and shape to semantic levels. To this end, we introduce a dataset named LENS to guide a VLM to follow the examination and check its readiness. Once the model is ready, we conduct the examination. Through this examination, we quantify and visualize VLMs' sensitivities to color and shape, and semantic matching. Our findings reveal that VLMs have varying sensitivity to different colors while consistently showing insensitivity to green across different VLMs. Also, we found different shape sensitivity and semantic recognition depending on LLM's capacity despite using the same fixed visual encoder. Our analyses and findings have potential to inspire the design of VLMs and the pre-processing of visual input to VLMs for improving application performance.