Hugging Face's logo

q-future
/
one-align

Zero-Shot Image Classification
Transformers
PyTorch
mplug_owl2
feature-extraction
custom_code
Model card Files Community
6
teowu commited on
Commit
3a518f4
•
1 Parent(s): b1ae627

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -1,10 +1,11 @@
1
  ---
2
  license: mit
 
3
  ---
4
 
5
  ## Quick Start with AutoModel
6
 
7
- For this image, ![](https://raw.githubusercontent.com/Q-Future/Q-Align/main/fig/singapore_flyer.jpg) start an AutoModel scorer with `transformers==4.31.0`:
8
 
9
  ```python
10
  import requests
@@ -55,5 +56,4 @@ From paper: `arxiv.org/abs/2312.17090`.
55
  | *FAST-VQA (ECCV 2022)* | 0.876/0.877 | 0.779/0.814 | 0.859/0.855 | 0.721/0.724 |
56
  | Q-Align (VQA) | 0.883/0.882 | 0.797/0.830 | 0.865/0.877 | 0.780/0.782 |
57
  | Q-Align (IQA+VQA) | 0.885/0.883 | 0.802/0.829 | 0.867/0.880 | **0.781**/**0.787** |
58
- | **OneAlign** (IQA+IAA+VQA) | **0.886**/**0.886** | **0.803**/**0.837** | **0.876**/**0.888** | **0.781**/0.786|
59
-
 
1
  ---
2
  license: mit
3
+ pipeline_tag: image-classification
4
  ---
5
 
6
  ## Quick Start with AutoModel
7
 
8
+ For this image, ![](https://raw.githubusercontent.com/Q-Future/Q-Align/main/fig/singapore_flyer.jpg) start an AutoModel scorer with `transformers==4.36.1`:
9
 
10
  ```python
11
  import requests
 
56
  | *FAST-VQA (ECCV 2022)* | 0.876/0.877 | 0.779/0.814 | 0.859/0.855 | 0.721/0.724 |
57
  | Q-Align (VQA) | 0.883/0.882 | 0.797/0.830 | 0.865/0.877 | 0.780/0.782 |
58
  | Q-Align (IQA+VQA) | 0.885/0.883 | 0.802/0.829 | 0.867/0.880 | **0.781**/**0.787** |
59
+ | **OneAlign** (IQA+IAA+VQA) | **0.886**/**0.886** | **0.803**/**0.837** | **0.876**/**0.888** | **0.781**/0.786|