Feature Extraction
Transformers
clip
vision
Inference Endpoints
uform-vl-english / README.md
kimihailv's picture
Update README.md
123769f verified
metadata
license: apache-2.0
pipeline_tag: feature-extraction
tags:
  - clip
  - vision
datasets:
  - sbu_captions
  - visual_genome
  - ChristophSchuhmann/MS_COCO_2017_URL_TEXT

UForm

Multi-Modal Inference Library
For Semantic Search Applications


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 English only model with:

  • 4 layers BERT (2 layers for unimodal encoding and rest layers for multimodal encoding)
  • ViT-B/16 (image resolution is 224x224)

If you need Multilingual model, check this.

Evaluation

The following metrics were obtained with multimodal re-ranking:

Dataset Recall@1 Recall@5 Recall@10
Zero-Shot Flickr 0.727 0.915 0.949
MS-COCO (train split was in training data) 0.510 0.761 0.838

Installation

pip install uform[torch]

Usage

To load the model:

import uform

model, processor = uform.get_model('unum-cloud/uform-vl-english')

To encode data:

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)

To get features:

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:

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 and Matching Score.

Cosine Similarity

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.

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.