AI-SAM: Automatic and Interactive Segment Anything Model
This addresses the problem of rigid segmentation approaches for computer vision practitioners by providing a hybrid solution, though it appears incremental as it builds on the Segment Anything Model.
The paper tackles the limitation of existing semantic segmentation models being either fully automatic or interactive by introducing AI-SAM, a novel paradigm that automatically generates initial prompts and allows user interaction, achieving state-of-the-art performance in automatic settings with flexibility for further improvement through user inputs.
Semantic segmentation is a core task in computer vision. Existing methods are generally divided into two categories: automatic and interactive. Interactive approaches, exemplified by the Segment Anything Model (SAM), have shown promise as pre-trained models. However, current adaptation strategies for these models tend to lean towards either automatic or interactive approaches. Interactive methods depend on prompts user input to operate, while automatic ones bypass the interactive promptability entirely. Addressing these limitations, we introduce a novel paradigm and its first model: the Automatic and Interactive Segment Anything Model (AI-SAM). In this paradigm, we conduct a comprehensive analysis of prompt quality and introduce the pioneering Automatic and Interactive Prompter (AI-Prompter) that automatically generates initial point prompts while accepting additional user inputs. Our experimental results demonstrate AI-SAM's effectiveness in the automatic setting, achieving state-of-the-art performance. Significantly, it offers the flexibility to incorporate additional user prompts, thereby further enhancing its performance. The project page is available at https://github.com/ymp5078/AI-SAM.