Update README.md
Browse files
README.md
CHANGED
|
@@ -4,7 +4,7 @@ datasets:
|
|
| 4 |
metrics:
|
| 5 |
- accuracy
|
| 6 |
---
|
| 7 |
-
CSATv2
|
| 8 |
|
| 9 |
CSATv2 is a lightweight high-resolution vision backbone designed to maximize throughput at 512×512 resolution.
|
| 10 |
By applying frequency-domain compression at the input stage, the model suppresses redundant spatial information and achieves extremely fast inference.
|
|
|
|
| 4 |
metrics:
|
| 5 |
- accuracy
|
| 6 |
---
|
| 7 |
+
# CSATv2
|
| 8 |
|
| 9 |
CSATv2 is a lightweight high-resolution vision backbone designed to maximize throughput at 512×512 resolution.
|
| 10 |
By applying frequency-domain compression at the input stage, the model suppresses redundant spatial information and achieves extremely fast inference.
|