Exploring Perceptual Limitation of Multimodal Large Language Models
This work addresses a critical gap in understanding MLLMs' perceptual boundaries, providing new evaluation protocols for researchers and developers in AI and computer vision, though it is incremental in building on prior anecdotal evidence.
The paper quantitatively studies the perceptual limitations of Multimodal Large Language Models (MLLMs) in answering visual questions about small objects, revealing that factors like object quality, size, location, and distractors significantly reduce accuracy, with controlled interventions showing these effects independently.
Multimodal Large Language Models (MLLMs) have recently shown remarkable perceptual capability in answering visual questions, however, little is known about the limits of their perception. In particular, while prior works have provided anecdotal evidence of MLLMs' sensitivity to object size, this phenomenon and its underlying causes have not been explored comprehensively. In this work, we quantitatively study the perception of small visual objects in several state-of-the-art MLLMs and reveal a pervasive limitation in answering questions about small objects in images. Next, we identify four independent factors that can contribute to this limitation -- object quality, size, distractors, and location -- and conduct controlled intervention studies to measure the effect of each factor on MLLMs' perception. In particular, we find that lower object quality and smaller object size can both independently reduce MLLMs' ability to answer visual questions. More surprisingly, we find that the location of the object in the image and the presence of visual distractors can also significantly reduce MLLMs' question answering accuracy. Our study provides a better understanding of the perceptual limitation of MLLMs and contributes new evaluation protocols for analyzing the perception of future MLLMs. To facilitate further investigations, we release our code and data.