Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
## Unmasked Token Alignment (UTA) for Efficient Visual-Language Representation Learning
|
2 |
|
3 |
This repository provides the inference code for our TMLR paper "Enhancing Vision-Language Model with Unmasked Token Alignment".
|
@@ -61,4 +69,4 @@ Contributions to this repository are welcome. Please feel free to open an issue
|
|
61 |
|
62 |
**Contact:**
|
63 |
|
64 |
-
If you have any questions or suggestions, please feel free to contact [Jihao Liu](https://jihaonew.github.io/) ([email](mailto:[email protected])).
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
datasets:
|
4 |
+
- imagenet-1k
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
pipeline_tag: zero-shot-classification
|
8 |
+
---
|
9 |
## Unmasked Token Alignment (UTA) for Efficient Visual-Language Representation Learning
|
10 |
|
11 |
This repository provides the inference code for our TMLR paper "Enhancing Vision-Language Model with Unmasked Token Alignment".
|
|
|
69 |
|
70 |
**Contact:**
|
71 |
|
72 |
+
If you have any questions or suggestions, please feel free to contact [Jihao Liu](https://jihaonew.github.io/) ([email](mailto:[email protected])).
|