zhirongw/lemniscate.pytorch
Unsupervised Feature Learning via Non-parametric Instance Discrimination
This project helps computer vision researchers extract meaningful visual characteristics from large collections of images without needing manual labels. It takes raw images as input and produces compact numerical representations (feature encodings) for each image. These representations can then be used to find visually similar images or categorize them, even when you don't have labeled data. This is ideal for researchers in computer vision or machine learning working with image datasets.
759 stars. No commits in the last 6 months.
Use this if you need to learn useful image features from vast amounts of unlabeled image data to enable tasks like image retrieval or classification without extensive human annotation.
Not ideal if you're looking for a ready-to-use application for image analysis without deep learning expertise, or if you already have fully labeled datasets for supervised learning.
Stars
759
Forks
133
Language
Python
License
—
Category
Last pushed
Mar 25, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zhirongw/lemniscate.pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification