Osprey: Pixel Understanding with Visual Instruction Tuning
This addresses the limitation of current MLLMs in pixel-level vision-language alignment for researchers and practitioners in computer vision and AI, representing a novel method for a known bottleneck rather than a foundational advancement.
The paper tackles the problem of achieving fine-grained pixel-level understanding in multimodal large language models (MLLMs) by proposing Osprey, a mask-text instruction tuning approach, which demonstrates superiority in region understanding tasks and integrates with Segment Anything Model for multi-granularity semantics.
Multimodal large language models (MLLMs) have recently achieved impressive general-purpose vision-language capabilities through visual instruction tuning. However, current MLLMs primarily focus on image-level or box-level understanding, falling short in achieving fine-grained vision-language alignment at pixel level. Besides, the lack of mask-based instruction data limits their advancements. In this paper, we propose Osprey, a mask-text instruction tuning approach, to extend MLLMs by incorporating fine-grained mask regions into language instruction, aiming at achieving pixel-wise visual understanding. To achieve this goal, we first meticulously curate a mask-based region-text dataset with 724K samples, and then design a vision-language model by injecting pixel-level representation into LLM. Specifically, Osprey adopts a convolutional CLIP backbone as the vision encoder and employs a mask-aware visual extractor to extract precise visual mask features from high resolution input. Experimental results demonstrate Osprey's superiority in various region understanding tasks, showcasing its new capability for pixel-level instruction tuning. In particular, Osprey can be integrated with Segment Anything Model (SAM) seamlessly to obtain multi-granularity semantics. The source code, dataset and demo can be found at https://github.com/CircleRadon/Osprey.