Image-Text Retrieval Embdding with ALBEF

author: David Wang

Description

This operator extracts features for image or text with ALBEF which can generate embeddings for text and image by jointly training an image encoder and text encoder to maximize the cosine similarity. This research introduced a contrastive loss to ALign the image and text representations BEfore Fusing (ALBEF) them through cross-modal attention, which enables more grounded vision and language representation learning. This repo is an adaptation from salesforce / ALBEF

Code Example

Load an image from path './teddy.jpg' to generate an image embedding.

Read the text 'A teddybear on a skateboard in Times Square.' to generate an text embedding.

Write the pipeline in simplified style:

from towhee import pipe, ops, DataCollection

img_pipe = (
    pipe.input('url')
    .map('url', 'img', ops.image_decode.cv2_rgb())
    .map('img', 'vec', ops.image_text_embedding.albef(model_name='albef_4m', modality='image')) 
    .output('img', 'vec')
)

text_pipe = (
    pipe.input('text')
    .map('text', 'vec', ops.image_text_embedding.albef(model_name='albef_4m', modality='text')) 
    .output('text', 'vec')
)

DataCollection(img_pipe('./teddy.jpg')).show()
DataCollection(text_pipe('A teddybear on a skateboard in Times Square.')).show()

Factory Constructor

Create the operator via the following factory method

albef(model_name, modality)

Parameters:

​ model_name: str

​ The model name of ALBEF. Supported model names:

• albef_4m
• albef_14m

​ modality: str

​ Which modality(image or text) is used to generate the embedding.

Interface

An image-text embedding operator takes a towhee image or string as input and generate an embedding in ndarray.

Parameters:

​ data: towhee.types.Image (a sub-class of numpy.ndarray) or str

​ The data (image or text based on specified modality) to generate embedding.

Returns: numpy.ndarray

​ The data embedding extracted by model.

More Resources

• The guide to instructor-xl | HKU NLP: instructor-xl: an instruction-finetuned model tailored for text embeddings with the best performance when compared to instructor-base and instructor-large.
• The guide to text-embedding-ada-002 model | OpenAI: text-embedding-ada-002: OpenAI's legacy text embedding model; average price/performance compared to text-embedding-3-large and text-embedding-3-small.
• The guide to mistral-embed | Mistral AI: mistral-embed: a specialized embedding model for text data with a context window of 8,000 tokens. Optimized for similarity retrieval and RAG applications.
• Supercharged Semantic Similarity Search in Production - Zilliz blog: Building a Blazing Fast, Highly Scalable Text-to-Image Search with CLIP embeddings and Milvus, the most advanced open-source vector database.
• The guide to clip-vit-base-patch32 | OpenAI: clip-vit-base-patch32: a CLIP multimodal model variant by OpenAI for image and text embedding.
• The guide to all-MiniLM-L12-v2 | Hugging Face: all-MiniLM-L12-v2: a text embedding model ideal for semantic search and RAG and fine-tuned based on Microsoft/MiniLM-L12-H384-uncased
• Sparse and Dense Embeddings: A Guide for Effective Information Retrieval with Milvus | Zilliz Webinar: Zilliz webinar covering what sparse and dense embeddings are and when you'd want to use one over the other.
• Image Embeddings for Enhanced Image Search - Zilliz blog: Image Embeddings are the core of modern computer vision algorithms. Understand their implementation and use cases and explore different image embedding models.
• Sparse and Dense Embeddings: A Guide for Effective Information Retrieval with Milvus | Zilliz Webinar: Zilliz webinar covering what sparse and dense embeddings are and when you'd want to use one over the other.