|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
- ar |
|
- hy |
|
- zh |
|
- fr |
|
- de |
|
- he |
|
- hi |
|
- id |
|
- it |
|
- ja |
|
- ko |
|
- fa |
|
- pl |
|
- pt |
|
- ru |
|
- es |
|
- th |
|
- tr |
|
- uk |
|
- vi |
|
pipeline_tag: feature-extraction |
|
tags: |
|
- clip |
|
- vision |
|
datasets: |
|
- sbu_captions |
|
- visual_genome |
|
- ChristophSchuhmann/MS_COCO_2017_URL_TEXT |
|
--- |
|
|
|
<h1 align="center">UForm</h1> |
|
<h3 align="center"> |
|
Multi-Modal Inference Library<br/> |
|
For Semantic Search Applications<br/> |
|
</h3> |
|
|
|
--- |
|
|
|
UForm is a Multi-Modal Modal Inference package, designed to encode Multi-Lingual Texts, Images, and, soon, Audio, Video, and Documents, into a shared vector space! |
|
|
|
This is model card of the __Multilingual model__ (21 languages) with: |
|
|
|
* 12 layers BERT (8 layers for unimodal encoding and rest layers for multimodal encoding) |
|
* ViT-B/16 (image resolution is 224x224) |
|
|
|
The model was trained on balanced multilingual dataset. |
|
|
|
If you need English model, check [this](https://huggingface.co/unum-cloud/uform-vl-english). |
|
|
|
## Evaluation |
|
|
|
For all evaluations, the multimodal part was used unless otherwise stated. |
|
|
|
**Monolingual** |
|
|
|
| Dataset | Recall@1 | Recall@5 | Recall@10 | |
|
| :-------- | ------: | --------: | --------: | |
|
| Zero-Shot Flickr | 0.558 | 0.813 | 0.874 | |
|
| MS-COCO (train split was in training data) | 0.401 | 0.680 | 0.781 | |
|
|
|
**Multilingual** |
|
|
|
[XTD-10](https://github.com/adobe-research/Cross-lingual-Test-Dataset-XTD10) |
|
|
|
Metric is recall@10 |
|
|
|
|
|
| English | German | Spanish | French | Italian | Russian | Japanese | Korean | Turkish | Chinese | Polish | |
|
| -------: | -------: | -------: | -------: | -------: | -------: | -------: | -------: | -------: | -------: | ------:| |
|
| 96.1 | 93.5 | 95.7 | 94.1 | 94.4 | 90.4 | 90.2 | 91.3 | 95.2 | 93.8 | 95.8 | |
|
|
|
|
|
[COCO-SM](https://github.com/kimihailv/coco-sm/tree/main) |
|
|
|
For this evaluation only unimodal part was used. |
|
|
|
Recall |
|
|
|
| Target Language | OpenCLIP @ 1 | UForm @ 1 | OpenCLIP @ 5 | UForm @ 5 | OpenCLIP @ 10 | UForm @ 10 | Speakers | |
|
| :-------------------- | -----------: | ------------: | -----------: | -------------:| ------------: | --------------:| -------: | |
|
| Arabic | 22.7 | **31.7** | 44.9 | **57.8** | 55.8 | **69.2** | 274 M | |
|
| Armenian | 5.6 | **22.0** | 14.3 | **44.7** | 20.2 | **56.0** | 4 M | |
|
| Chinese | 27.3 | **32.2** | 51.3 | **59.0** | 62.1 | **70.5** | 1'118 M | |
|
| English | **37.8** | 37.7 | 63.5 | **65.0** | 73.5 | **75.9** | 1'452 M | |
|
| French | 31.3 | **35.4** | 56.5 | **62.6** | 67.4 | **73.3** | 274 M | |
|
| German | 31.7 | **35.1** | 56.9 | **62.2** | 67.4 | **73.3** | 134 M | |
|
| Hebrew | 23.7 | **26.7** | 46.3 | **51.8** | 57.0 | **63.5** | 9 M | |
|
| Hindi | 20.7 | **31.3** | 42.5 | **57.9** | 53.7 | **69.6** | 602 M | |
|
| Indonesian | 26.9 | **30.7** | 51.4 | **57.0** | 62.7 | **68.6** | 199 M | |
|
| Italian | 31.3 | **34.9** | 56.7 | **62.1** | 67.1 | **73.1** | 67 M | |
|
| Japanese | 27.4 | **32.6** | 51.5 | **59.2** | 62.6 | **70.6** | 125 M | |
|
| Korean | 24.4 | **31.5** | 48.1 | **57.8** | 59.2 | **69.2** | 81 M | |
|
| Persian | 24.0 | **28.8** | 47.0 | **54.6** | 57.8 | **66.2** | 77 M | |
|
| Polish | 29.2 | **33.6** | 53.9 | **60.1** | 64.7 | **71.3** | 41 M | |
|
| Portuguese | 31.6 | **32.7** | 57.1 | **59.6** | 67.9 | **71.0** | 257 M | |
|
| Russian | 29.9 | **33.9** | 54.8 | **60.9** | 65.8 | **72.0** | 258 M | |
|
| Spanish | 32.6 | **35.6** | 58.0 | **62.8** | 68.8 | **73.7** | 548 M | |
|
| Thai | 21.5 | **28.7** | 43.0 | **54.6** | 53.7 | **66.0** | 61 M | |
|
| Turkish | 25.5 | **33.0** | 49.1 | **59.6** | 60.3 | **70.8** | 88 M | |
|
| Ukranian | 26.0 | **30.6** | 49.9 | **56.7** | 60.9 | **68.1** | 41 M | |
|
| Vietnamese | 25.4 | **28.3** | 49.2 | **53.9** | 60.3 | **65.5** | 85 M | |
|
| | | | | | | | | |
|
| Mean | 26.5±6.4 | **31.8±3.5** | 49.8±9.8 | **58.1±4.5** | 60.4±10.6 | **69.4±4.3** | - | |
|
| Google Translate | 27.4±6.3 | **31.5±3.5** | 51.1±9.5 | **57.8±4.4** | 61.7±10.3 | **69.1±4.3** | - | |
|
| Microsoft Translator | 27.2±6.4 | **31.4±3.6** | 50.8±9.8 | **57.7±4.7** | 61.4±10.6 | **68.9±4.6** | - | |
|
| Meta NLLB | 24.9±6.7 | **32.4±3.5** | 47.5±10.3 | **58.9±4.5** | 58.2±11.2 | **70.2±4.3** | - | |
|
|
|
NDCG@20 |
|
|
|
| | Arabic | Armenian | Chinese | French | German | Hebrew | Hindi | Indonesian | Italian | Japanese | Korean | Persian | Polish | Portuguese | Russian | Spanish | Thai | Turkish | Ukranian | Vietnamese | Mean (all) | Mean (Google Translate) | Mean(Microsoft Translator) | Mean(NLLB) |
|
| :------------ | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | |
|
| OpenCLIP NDCG | 0.639 | 0.204 | 0.731 | 0.823 | 0.806 | 0.657 | 0.616 | 0.733 | 0.811 | 0.737 | 0.686 | 0.667 | 0.764 | 0.832 | 0.777 | 0.849 | 0.606 | 0.701 | 0.704 | 0.697 | 0.716 ± 0.149 | 0.732 ± 0.145 | 0.730 ± 0.149 | 0.686 ± 0.158 |
|
| UForm NDCG | 0.868 | 0.691 | 0.880 | 0.932 | 0.927 | 0.791 | 0.879 | 0.870 | 0.930 | 0.885 | 0.869 | 0.831 | 0.897 | 0.897 | 0.906 | 0.939 | 0.822 | 0.898 | 0.851 | 0.818 | 0.875 ± 0.064 | 0.869 ± 0.063 | 0.869 ± 0.066 | 0.888 ± 0.064 |
|
|
|
## Installation |
|
|
|
```bash |
|
pip install uform |
|
``` |
|
|
|
## Usage |
|
|
|
To load the model: |
|
|
|
```python |
|
import uform |
|
|
|
model, processor = uform.get_model('unum-cloud/uform-vl-multilingual-v2') |
|
``` |
|
|
|
To encode data: |
|
|
|
```python |
|
from PIL import Image |
|
|
|
text = 'a small red panda in a zoo' |
|
image = Image.open('red_panda.jpg') |
|
|
|
image_data = processor.preprocess_image(image) |
|
text_data = processor.preprocess_text(text) |
|
|
|
image_features, image_embedding = model.encode_image(image_data, return_features=True) |
|
text_features, text_embedding = model.encode_text(text_data, return_features=True) |
|
joint_embedding = model.encode_multimodal(image=image_data, text=text_data) |
|
``` |
|
|
|
To get features: |
|
|
|
```python |
|
image_features, image_embedding = model.encode_image(image_data, return_features=True) |
|
text_features, text_embedding = model.encode_text(text_data, return_features=True) |
|
``` |
|
|
|
These features can later be used to produce joint multimodal encodings faster, as the first layers of the transformer can be skipped: |
|
|
|
```python |
|
joint_embedding = model.encode_multimodal( |
|
image_features=image_features, |
|
text_features=text_features, |
|
attention_mask=text_data['attention_mask'] |
|
) |
|
``` |
|
|
|
There are two options to calculate semantic compatibility between an image and a text: [Cosine Similarity](#cosine-similarity) and [Matching Score](#matching-score). |
|
|
|
### Cosine Similarity |
|
|
|
```python |
|
import torch.nn.functional as F |
|
|
|
similarity = F.cosine_similarity(image_embedding, text_embedding) |
|
``` |
|
|
|
The `similarity` will belong to the `[-1, 1]` range, `1` meaning the absolute match. |
|
|
|
__Pros__: |
|
|
|
- Computationally cheap. |
|
- Only unimodal embeddings are required, unimodal encoding is faster than joint encoding. |
|
- Suitable for retrieval in large collections. |
|
|
|
__Cons__: |
|
|
|
- Takes into account only coarse-grained features. |
|
|
|
|
|
### Matching Score |
|
|
|
Unlike cosine similarity, unimodal embedding are not enough. |
|
Joint embedding will be needed and the resulting `score` will belong to the `[0, 1]` range, `1` meaning the absolute match. |
|
|
|
```python |
|
score = model.get_matching_scores(joint_embedding) |
|
``` |
|
|
|
__Pros__: |
|
|
|
- Joint embedding captures fine-grained features. |
|
- Suitable for re-ranking – sorting retrieval result. |
|
|
|
__Cons__: |
|
|
|
- Resource-intensive. |
|
- Not suitable for retrieval in large collections. |
