README.md
CHANGED
|
@@ -1,3 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Hiera Encoder from Meta's SAM2.1 (Segment Anything Model)
|
| 2 |
|
| 3 |
Meta's [SAM2 (Segment Anything Model v2)](https://github.com/facebookresearch/sam2) demonstrates state-of-the-art video segmentation capabilities. A core component enabling this is the **Hiera** module, which, through supervised training on object segmentation, has learned a strong understanding of hierarchical visual features.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- vision
|
| 5 |
+
- image-segmentation
|
| 6 |
+
- hierarchical
|
| 7 |
+
- encoder
|
| 8 |
+
- sam2
|
| 9 |
+
- meta
|
| 10 |
+
- pytorch
|
| 11 |
+
- huggingface-compatible
|
| 12 |
+
---
|
| 13 |
# Hiera Encoder from Meta's SAM2.1 (Segment Anything Model)
|
| 14 |
|
| 15 |
Meta's [SAM2 (Segment Anything Model v2)](https://github.com/facebookresearch/sam2) demonstrates state-of-the-art video segmentation capabilities. A core component enabling this is the **Hiera** module, which, through supervised training on object segmentation, has learned a strong understanding of hierarchical visual features.
|