Promoting Segment Anything Model towards Highly Accurate Dichotomous Image Segmentation

arXiv:2401.00248v2 Announce Type: replace
Abstract: The Segment Anything Model (SAM) represents a significant breakthrough into foundation models for computer vision, providing a large-scale image segmentation model. However, despite SAM's zero-shot performance, its segmentation masks lack fine-grained details, particularly in accurately delineating object boundaries. We have high expectations regarding whether SAM, as a foundation model, can be improved towards highly accurate object segmentation, which is known as dichotomous image segmentation (DIS). To address this issue, we propose DIS-SAM, which advances SAM …

abstract arxiv computer computer vision cs.ai cs.cv fine-grained foundation however image masks object performance sam scale segment segment anything segment anything model segmentation type vision zero-shot