370
edits
Segment Anything Model and Dataset (SAM and SA-1B): Difference between revisions
Segment Anything Model and Dataset (SAM and SA-1B) (view source)
Revision as of 15:14, 9 April 2023
, 9 April 2023no edit summary
No edit summary |
No edit summary |
||
| Line 60: | Line 60: | ||
==Segmenting 1 Billion Masks: Building SA-1B Dataset== | ==Segmenting 1 Billion Masks: Building SA-1B Dataset== | ||
[[File:segment anything dataset1.png|400px|right]] | |||
To train SAM, a massive and diverse dataset was needed. The SA-1B dataset was collected using the model itself; annotators used SAM to annotate images interactively, and the newly annotated data was then used to update SAM. This process was repeated multiple times to iteratively improve both the model and the [[dataset]]. | To train SAM, a massive and diverse dataset was needed. The SA-1B dataset was collected using the model itself; annotators used SAM to annotate images interactively, and the newly annotated data was then used to update SAM. This process was repeated multiple times to iteratively improve both the model and the [[dataset]]. | ||