davidsvy/hard-negative-mixing
An unofficial PyTorch implementation of the NeurIPS 2020 paper Hard Negative Mixing for Contrastive Learning.
This project helps machine learning engineers improve their image recognition models by training them more effectively without labeled data. It takes in images and outputs a more robust model that can better distinguish between similar but different visual concepts. The end-user is a machine learning engineer working on computer vision tasks.
No commits in the last 6 months.
Use this if you are a machine learning engineer looking to enhance the performance of your contrastive learning models, especially for image datasets, by generating more challenging negative examples during training.
Not ideal if you are not familiar with PyTorch or the concepts of contrastive learning and representation learning.
Stars
20
Forks
4
Language
Python
License
MIT
Category
Last pushed
Oct 17, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/davidsvy/hard-negative-mixing"
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)