Multimodal

SegGPT: Segmenting Everything In Context

First page

Paper summary

Unifies segmentation tasks into a generalist in-context model.

Ask this paper

Key points

In-context segmentation: Uses in-context examples (input-mask pairs) to define the segmentation task at inference time.

Task generalization: Handles semantic, instance, panoptic, and referring segmentation through the same in-context interface.

Training-free adaptation: Adapts to new segmentation tasks without retraining - just provide example pairs.

Prompt-based vision: Part of the 2023 push to bring LLM-style in-context learning to vision tasks.

Every Monday