SegGPT: Segmenting Everything In Context
arXiv:2304.03284
Abstract
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.
arXiv commentCode and Demo: https://github.com/baaivision/Painter
Cited by in corpus (4)
- 3DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentation
- UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility
- GLIMS: Attention-Guided Lightweight Multi-Scale Hybrid Network for Volumetric Semantic Segmentation
- UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything Model