mesnico/ALADIN
Official implementation of the paper "ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval"
This tool helps researchers and engineers improve how computers match images with descriptive text. It takes a collection of images and corresponding text descriptions and trains a model to understand their relationships more efficiently. The end-user is typically a computer vision researcher or machine learning engineer working on content-based retrieval systems.
No commits in the last 6 months.
Use this if you need to build or evaluate systems that accurately find images based on text queries or vice-versa, with a focus on improving model efficiency.
Not ideal if you are looking for an out-of-the-box application for general image search or a solution that doesn't require deep machine learning expertise to implement.
Stars
28
Forks
7
Language
Python
License
MIT
Category
Last pushed
Dec 06, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/mesnico/ALADIN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
princeton-nlp/SimCSE
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
n-waves/multifit
The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model...
yxuansu/SimCTG
[NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation
alibaba-edu/simple-effective-text-matching
Source code of the ACL2019 paper "Simple and Effective Text Matching with Richer Alignment Features".
Shark-NLP/OpenICL
OpenICL is an open-source framework to facilitate research, development, and prototyping of...