SegGPT: Segmenting Everything In Context
This addresses the need for a versatile segmentation tool for computer vision researchers and practitioners, though it is incremental as it builds on existing in-context learning paradigms.
SegGPT tackles the problem of unifying various segmentation tasks into a single generalist model by using an in-context learning framework, achieving strong performance on tasks like few-shot semantic segmentation and panoptic segmentation.
We present SegGPT, a generalist model for segmenting everything in context. We unify various segmentation tasks into a generalist in-context learning framework that accommodates different kinds of segmentation data by transforming them into the same format of images. The training of SegGPT is formulated as an in-context coloring problem with random color mapping for each data sample. The objective is to accomplish diverse tasks according to the context, rather than relying on specific colors. After training, SegGPT can perform arbitrary segmentation tasks in images or videos via in-context inference, such as object instance, stuff, part, contour, and text. SegGPT is evaluated on a broad range of tasks, including few-shot semantic segmentation, video object segmentation, semantic segmentation, and panoptic segmentation. Our results show strong capabilities in segmenting in-domain and out-of-domain targets, either qualitatively or quantitatively.