OpenAlex · Aktualisierung stündlich · Letzte Aktualisierung: 18.03.2026, 13:55

Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.

Segment Anything

2023·7.976 Zitationen
Volltext beim Verlag öffnen

7.976

Zitationen

12

Autoren

2023

Jahr

Abstract

We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest segmentation dataset to date (by far), with over 1 billion masks on 11M licensed and privacy respecting images. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks. We evaluate its capabilities on numerous tasks and find that its zero-shot performance is impressive – often competitive with or even superior to prior fully supervised results. We are releasing the Segment Anything Model (SAM) and corresponding dataset (SA-1B) of 1B masks and 11M images at segment-anything.com to foster research into foundation models for computer vision. We recommend reading the full paper at: arxiv.org/abs/2304.02643.

Ähnliche Arbeiten

Autoren

Themen

Advanced Neural Network ApplicationsVisual Attention and Saliency DetectionAdversarial Robustness in Machine Learning
Volltext beim Verlag öffnen