Do we Really Need Visual Instructions? Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models
This work addresses the challenge of reducing data collection costs and improving efficiency in fine-tuning large vision-language models for multimodal tasks, representing an incremental improvement over existing methods.
The paper tackles the problem of costly visual instruction tuning for large vision-language models by proposing ViFT, a visual instruction-free fine-tuning framework that uses only text instructions and image captions during training, achieving state-of-the-art performance on visual reasoning and instruction following benchmarks with less training data.
Visual instruction tuning has become the predominant technology in eliciting the multimodal task-solving capabilities of large vision-language models (LVLMs). Despite the success, as visual instructions require images as the input, it would leave the gap in inheriting the task-solving capabilities from the backbone LLMs, and make it costly to collect a large-scale dataset. To address it, we propose ViFT, a visual instruction-free fine-tuning framework for LVLMs. In ViFT, we only require the text-only instructions and image caption data during training, to separately learn the task-solving and visual perception abilities. During inference, we extract and combine the representations of the text and image inputs, for fusing the two abilities to fulfill multimodal tasks. Experimental results demonstrate that ViFT can achieve state-of-the-art performance on several visual reasoning and visual instruction following benchmarks, with rather less training data. Our code and data will be publicly released.