Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains
This addresses the challenge of handling intricate multi-image scenarios for vision-language systems, representing a significant but incremental step toward more robust models.
The paper tackles the problem of vision-language models struggling with multi-image inputs by introducing Focus-Centric Visual Chain, a novel paradigm that improves perception, comprehension, and reasoning, resulting in average performance gains of 3.16% and 2.24% across seven benchmarks without harming general capabilities.
Vision-language models (VLMs) achieve remarkable success in single-image tasks. However, real-world scenarios often involve intricate multi-image inputs, leading to a notable performance decline as models struggle to disentangle critical information scattered across complex visual features. In this work, we propose Focus-Centric Visual Chain, a novel paradigm that enhances VLMs'perception, comprehension, and reasoning abilities in multi-image scenarios. To facilitate this paradigm, we propose Focus-Centric Data Synthesis, a scalable bottom-up approach for synthesizing high-quality data with elaborate reasoning paths. Through this approach, We construct VISC-150K, a large-scale dataset with reasoning data in the form of Focus-Centric Visual Chain, specifically designed for multi-image tasks. Experimental results on seven multi-image benchmarks demonstrate that our method achieves average performance gains of 3.16% and 2.24% across two distinct model architectures, without compromising the general vision-language capabilities. our study represents a significant step toward more robust and capable vision-language systems that can handle complex visual scenarios.