Search papers, labs, and topics across Lattice.
This paper introduces FoRIS, a training-free framework for In-Context Segmentation (ICS) that employs a progressive refinement approach to enhance segmentation accuracy. By decomposing the segmentation process into three distinct stages鈥擣oreground Purification, Foreground Localization, and Foreground Consolidation鈥擣oRIS effectively reduces background noise and improves the precision of segmented structures. Experimental results indicate that FoRIS achieves state-of-the-art performance, surpassing existing methods by an average of 4.5 and 4.8 mIoU points in 1-shot and 5-shot scenarios, respectively.
FoRIS redefines in-context segmentation by transforming it into a progressive refinement process, achieving state-of-the-art results without the need for training.
In-Context Segmentation (ICS) aims to precisely segment arbitrary semantic concepts, such as objects or parts, given one or a few annotated visual exemplars. In this paper, we revisit ICS from a more classical segmentation perspective, viewing it as a coarse-to-fine progressive refinement process. Rather than directly predicting the final mask through reference-query matching, we progressively refine the segmentation from coarse and ambiguous foreground responses to precise and complete foreground structures. Building upon this perspective, we propose a training-free in-context segmentation framework, termed FoRIS. Specifically, FoRIS consists of three key stages: Foreground Purification, Foreground Localization, and Foreground Consolidation, which progressively suppress background distractions, localize discriminative target regions, and recover complete foreground structures through semantic aggregation. Experimental results demonstrate that FoRIS achieves SOTA performance across semantic and part segmentation tasks, with average improvements of 4.5 and 4.8 mIoU points over existing approaches in the 1-shot and 5-shot settings, respectively. Code: https://github.com/Xi-Mu-Yu/FoRIS.
