Lenna: Language Enhanced Reasoning Detection Assistant
This work addresses the need for better reasoning-based detection in AI systems for computer vision applications, representing an incremental improvement by adapting existing MLLM frameworks.
The paper tackles the problem of underutilizing reasoning power and world knowledge in multimodal large language models for image perception by proposing Lenna, a language-enhanced reasoning detection assistant that incorporates a <DET> token to preserve location information, achieving outstanding performance on the ReasonDet dataset with low training costs and minimal transferring overhead.
With the fast-paced development of multimodal large language models (MLLMs), we can now converse with AI systems in natural languages to understand images. However, the reasoning power and world knowledge embedded in the large language models have been much less investigated and exploited for image perception tasks. In this paper, we propose Lenna, a language-enhanced reasoning detection assistant, which utilizes the robust multimodal feature representation of MLLMs, while preserving location information for detection. This is achieved by incorporating an additional <DET> token in the MLLM vocabulary that is free of explicit semantic context but serves as a prompt for the detector to identify the corresponding position. To evaluate the reasoning capability of Lenna, we construct a ReasonDet dataset to measure its performance on reasoning-based detection. Remarkably, Lenna demonstrates outstanding performance on ReasonDet and comes with significantly low training costs. It also incurs minimal transferring overhead when extended to other tasks. Our code and model will be available at https://git.io/Lenna.