SOURCE-LINKED INTELLIGENCE

Diffuse2Seg: Diffusion Models Can Segment Anything Without Supervision

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Open-world entity segmentation aims to predict masks for arbitrary objects across domains and at multiple granularities, from parts to whole objects. In this setting, SAM sets a strong standard: trained on SA-1B, comprising 11M images and over 1B carefully annotated masks, it achieves remarkable zero-shot performance. Collecting such labels is expensive and time-consuming, however, which limits how far this recipe can scale. Text-to-image diffusion models offer a way around this. Their intermediate features transfer well across perception tasks, and since object structure emerges as the model

Read original source ↗ Open in workspace

recordType

paper

region

Global