AI-SAM: Automatic and Interactive Segment Anything Model
Yimu Pan, Sitao Zhang, Alison D. Gernand, Jeffery A. Goldstein, James Z. Wang
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/ymp5078/ai-samOfficialIn paperpytorch★ 21
Abstract
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| Automatic Cardiac Diagnosis Challenge (ACDC) | Interactive AI-SAM gt box | Avg DSC | 93.89 | — | Unverified |
| Automatic Cardiac Diagnosis Challenge (ACDC) | Automatic AI-SAM | Avg DSC | 92.06 | — | Unverified |
| Synapse multi-organ CT | Interactive AI-SAM gt box | Avg DSC | 90.66 | — | Unverified |
| Synapse multi-organ CT | Automatic AI-SAM | Avg DSC | 84.21 | — | Unverified |