vikasverma1077/manifold_mixup

Code for reproducing Manifold Mixup results (ICML 2019)

/ 100

Emerging

This project helps machine learning researchers and practitioners train more robust and accurate deep learning models. By interpolating between the hidden states of different data examples during training, it produces more discriminative and compact data representations. This leads to models that perform better on various supervised learning tasks.

492 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer looking to improve the generalization and robustness of your deep learning models, especially for image classification or other supervised learning tasks.

Not ideal if you are not working with deep learning models or are primarily focused on semi-supervised learning, for which a different project from the same authors is recommended.

deep-learning model-training representation-learning supervised-learning model-robustness

No License Stale 6m No Package No Dependents

Maintenance 0 / 25

Adoption 10 / 25

Maturity 8 / 25

Community 18 / 25

How are scores calculated?

Stars

492

Forks

Language

Python

License

—

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)

Explore ML Frameworks

All categories Trending ML Framework directory Insights