Segment Anything
We present the Segment Anything (SA) project: a promptable segmentation model, dataset, and task advancing foundation models in computer vision. The Segment Anything Model (SAM) processes diverse prompts (points, boxes, text) through a ViT-based encoder and real-time mask decoder (~50ms per prompt),...
| Published in: | Инноватика-2025 : сборник материалов XXI Международной школы-конференции студентов, аспирантов и молодых ученых, 28-30 апреля 2025 г., г. Томск, Россия С. 255-262 |
|---|---|
| Main Author: | |
| Format: | Book Chapter |
| Language: | English |
| Subjects: | |
| Online Access: | https://vital.lib.tsu.ru/vital/access/manager/Repository/koha:001272904 Перейти в каталог НБ ТГУ |
| LEADER | 02183naa a2200301 c 4500 | ||
|---|---|---|---|
| 001 | koha001272904 | ||
| 005 | 20251218181128.0 | ||
| 007 | cr | | ||
| 008 | 251216s2025 ru fs 100 0 eng d | ||
| 035 | |a koha001272904 | ||
| 040 | |a RU-ToGU |b rus |c RU-ToGU | ||
| 100 | 1 | |a Li, Yuxuan |9 1013497 | |
| 245 | 1 | 0 | |a Segment Anything |c Li Yuxuan |
| 336 | |a Текст | ||
| 337 | |a электронный | ||
| 504 | |a Библиогр.: 9 назв. | ||
| 520 | 3 | |a We present the Segment Anything (SA) project: a promptable segmentation model, dataset, and task advancing foundation models in computer vision. The Segment Anything Model (SAM) processes diverse prompts (points, boxes, text) through a ViT-based encoder and real-time mask decoder (~50ms per prompt), resolving ambiguity via multi-mask outputs. Trained on SA-1B-1.1B masks from 11M licensed images collected via a scalable data engine-SAM achieves human-level mask quality (94% IoU vs. professional edits). Zero-shot evaluations across 23 benchmarks demonstrate strong performance: surpassing RITM in point-based segmentation (human-rated), 0.768 ODS edge detection on BSDS500, and 59.3 AR@1000 object proposals on LVIS. SAM enables flexible integration into systems for tasks like text-guided segmentation. We release models and data to catalyze vision foundation model research. | |
| 653 | |a базовые модели | ||
| 653 | |a сегментация | ||
| 653 | |a оперативное проектирование | ||
| 655 | 4 | |a статьи в сборниках | |
| 773 | 0 | |t Инноватика-2025 : сборник материалов XXI Международной школы-конференции студентов, аспирантов и молодых ученых, 28-30 апреля 2025 г., г. Томск, Россия |d Томск, 2025 |g С. 255-262 |z 9785936297311 |w koha001268951 | |
| 852 | 4 | |a RU-ToGU | |
| 856 | 4 | |u https://vital.lib.tsu.ru/vital/access/manager/Repository/koha:001272904 | |
| 856 | |y Перейти в каталог НБ ТГУ |u https://koha.lib.tsu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=1272904 | ||
| 908 | |a статья | ||
| 039 | |b 100 | ||
| 999 | |c 1272904 |d 1272904 | ||