SegGPT: Segmenting Everything In Context
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
Key pointsUnifies segmentation tasks into a generalist in-context model.
01
In-context segmentation: Uses in-context examples (input-mask pairs) to define the segmentation task at inference time.
02
Task generalization: Handles semantic, instance, panoptic, and referring segmentation through the same in-context interface.
03
Training-free adaptation: Adapts to new segmentation tasks without retraining - just provide example pairs.
04
Prompt-based vision: Part of the 2023 push to bring LLM-style in-context learning to vision tasks.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack