SAMAug: Point Prompt Augmentation for Segment Anything Model
This work addresses the need for more effective interactive segmentation tools in computer vision, though it is incremental as it builds upon the existing SAM framework.
The paper tackles the problem of enhancing interactive image segmentation performance by introducing SAMAug, a visual point augmentation method for the Segment Anything Model (SAM), which generates augmented point prompts to improve segmentation accuracy, with results showing boosted performance on datasets like COCO and ISIC2018 using strategies such as maximum distance and saliency.
This paper introduces SAMAug, a novel visual point augmentation method for the Segment Anything Model (SAM) that enhances interactive image segmentation performance. SAMAug generates augmented point prompts to provide more information about the user's intention to SAM. Starting with an initial point prompt, SAM produces an initial mask, which is then fed into our proposed SAMAug to generate augmented point prompts. By incorporating these extra points, SAM can generate augmented segmentation masks based on both the augmented point prompts and the initial prompt, resulting in improved segmentation performance. We conducted evaluations using four different point augmentation strategies: random sampling, sampling based on maximum difference entropy, maximum distance, and saliency. Experiment results on the COCO, Fundus, COVID QUEx, and ISIC2018 datasets show that SAMAug can boost SAM's segmentation results, especially using the maximum distance and saliency. SAMAug demonstrates the potential of visual prompt augmentation for computer vision. Codes of SAMAug are available at github.com/yhydhx/SAMAug