VCM: Vision Concept Modeling Based on Implicit Contrastive Learning with Vision-Language Instruction Fine-Tuning
This addresses a bottleneck in real-world AI applications like embodied intelligence by improving efficiency, though it is an incremental advancement building on existing LVLM methods.
The paper tackles the inefficiency of large vision-language models (LVLMs) in processing images at the token level by proposing VCM, a self-supervised visual concept modeling framework that reduces computational costs by 85% for LLaVA-1.5-7B while maintaining strong performance across image understanding tasks.
Large Vision-Language Models (LVLMs) are pivotal for real-world AI tasks like embodied intelligence due to their strong vision-language reasoning abilities. However, current LVLMs process entire images at the token level, which is inefficient compared to humans who analyze information and generate content at the conceptual level, extracting relevant visual concepts with minimal effort. This inefficiency, stemming from the lack of a visual concept model, limits LVLMs' usability in real-world applications. To address this, we propose VCM, an end-to-end self-supervised visual concept modeling framework. VCM leverages implicit contrastive learning across multiple sampled instances and vision-language fine-tuning to construct a visual concept model without requiring costly concept-level annotations. Our results show that VCM significantly reduces computational costs (e.g., 85\% fewer FLOPs for LLaVA-1.5-7B) while maintaining strong performance across diverse image understanding tasks. Moreover, VCM enhances visual encoders' capabilities in classic visual concept perception tasks. Extensive quantitative and qualitative experiments validate the effectiveness and efficiency of VCM.