winci-ai/resa
An official implementation of ReSA (ICML 2025)
ReSA helps machine learning practitioners efficiently train image recognition models without needing large amounts of labeled data. It takes raw, unlabeled image datasets and produces highly effective image encoders. These encoders can then be used for various downstream tasks like classifying images into categories or identifying specific objects within them.
Use this if you need to build robust image classification or recognition systems, especially when acquiring vast amounts of labeled image data is impractical or too expensive.
Not ideal if your primary goal is natural language processing or tabular data analysis, as this project is specifically designed for computer vision tasks.
Stars
25
Forks
3
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 23, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/winci-ai/resa"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Westlake-AI/openmixup
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
YU1ut/MixMatch-pytorch
Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"
kamata1729/QATM_pytorch
Pytorch Implementation of QATM:Quality-Aware Template Matching For Deep Learning
nttcslab/msm-mae
Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations
rgeirhos/generalisation-humans-DNNs
Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)