[HN Gopher] Segment Anything Model and Friends
___________________________________________________________________
Segment Anything Model and Friends
Author : sauravmaheshkar
Score : 49 points
Date : 2024-08-07 12:22 UTC (4 days ago)
(HTM) web link (www.lightly.ai)
(TXT) w3m dump (www.lightly.ai)
| GaggiX wrote:
| SAM 2 not only focuses on speed, it actually performs better than
| SAM (1), the other models instead always trade performance for
| speed. SAM 2 is able to achieve this result thanks to its Hiera
| MAE encoder: https://arxiv.org/abs/2306.00989
| OkGoDoIt wrote:
| I appreciate this overview, but something that isn't clear to me
| is how SAM 2 compares to efficient SAM and the other improvements
| that are based on SAM 1? Is SAM 2 better across-the-board or is
| it better than SAM 1 but not a slam dunk compared to efficient
| SAM and the others? Especially as it relates to speed and model
| size. Should we wait for someone to make an efficient SAM 2?
| rocauc wrote:
| SAM 2's key contribution is adding time-based segmentation to
| apply to videos. Even on images alone, the authors note [0] the
| image-based segmentation benchmark does exceed SAM 1
| performance. There have been some weaknesses exposed in areas
| of SAM 2 vs SAM 1, like potentially medical images [1].
| Efficient SAM trades SAM 1 accuracy for ~40x speedup. I suspect
| we will soon see Efficient SAM 2.
|
| [0] https://x.com/josephofiowa/status/1818087122517311864 [1]
| https://x.com/bowang87/status/1821021898928443520?s=46&t=9K-...
___________________________________________________________________
(page generated 2024-08-11 23:00 UTC)