Segment Anything

被引：2768

作者：

Kirillov, Alexander ^{[1
]}

Mintun, Eric ^{[1
]}

Ravi, Nikhila ^{[1
]}

Mao, Hanzi ^{[1
]}

Rolland, Chloe ^{[1
]}

Gustafson, Laura ^{[1
]}

Xiao, Tete ^{[1
]}

Whitehead, Spencer ^{[1
]}

Berg, Alexander C. ^{[1
]}

Lo, Wan-Yen ^{[1
]}

Dolla'r, Piotr ^{[1
]}

Girshick, Ross ^{[1
]}

机构：

[1] Meta AI Res, FAIR, Menlo Pk, CA 94025 USA

来源：

2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV | 2023年

关键词：

D O I：

10.1109/ICCV51070.2023.00371

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：3992 / 4003

页数：12

共 115 条

[1]

Adelson Edward H, 2001, HUMAN VISION ELECT I, V2

[2]

Alexe B, 2010, PROC CVPR IEEE, P73, DOI 10.1109/CVPR.2010.5540226

[3]

[Anonymous], 2021, ICML

[4]

[Anonymous], 2021, CVPR, DOI DOI 10.1109/CVPR46437.2021.00294

[5]

[Anonymous], 2016, CVPR, DOI DOI 10.1109/CVPR.2016.97

[6]

[Anonymous], 2021, ICML

[7]

[Anonymous], ICCV, DOI DOI 10.1109/ICCV.2017.299

[8]

[Anonymous], 2019, CVPR, DOI DOI 10.1109/CVPR.2019.00550

[9] Contour Detection and Hierarchical Image Segmentation [J].

Arbelaez, Pablo ;

Maire, Michael ;

Fowlkes, Charless ;

Malik, Jitendra .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2011, 33 (05) :898-916

[10]

Ba J.L., 2016, Layer Normalization

← 1 2 3 4 5 6 7 8 9 10 →