PyTorch implementation of CNNs for CIFAR benchmark

CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark

face recognition training project(pytorch)

Implementation of the mixup training method

TextAugment: Text Augmentation Library

🛠 Toolbox to extend PyTorch functionalities

An implementation of "mixup: Beyond Empirical Risk Minimization"

[Survey] Awesome List of Mixup Augmentation and Beyond (https://arxiv.org/abs/2409.05202)

Official PyTorch implementation of "Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup" (ICML'20)

Official PyTorch implementation of DiffuseMix : Label-Preserving Data Augmentation with Diffusion Models (CVPR'2024)

SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data (AAAI 2021)

Official PyTorch implementation of "Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity" (ICLR'21 Oral)

[CVPR 2022] CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervision

mixup: Beyond Empirical Risk Minimization

Data Augmentation For Object Detection using Pytorch and PIL

Official Implementation of AlignMixup - CVPR 2022

Pseudo-Bag Mixup Augmentation for Multiple Instance Learning-Based Whole Slide Image Classification (IEEE TMI 2024)

[IJCAI 2023] Co-training with High-Confidence Pseudo Labels for Semi-supervised Medical Image Segmentation

An implementation of MobileNetV3 with pyTorch

Official pytorch implementation of NeurIPS 2022 paper, TokenMixup

Source codes for the paper "Local Additivity Based Data Augmentation for Semi-supervised NER"

an implementation of mixup

Official adversarial mixup resynthesis repository

Implementation of modern data augmentation techniques in TensorFlow 2.x to be used in your training pipeline.

[TAI 2023] Contrastive Domain Adaptation for Time-Series via Temporal Mixup

Exploring mixup strategies for text classification

A pytorch implementation for "Neighborhood Collective Estimation for Noisy Label Identification and Correction", which is accepted by ECCV2022.

Review materials for the TWiML Study Group. Contains annotated versions of the original Jupyter noteboooks (look for names like *_jcat.ipynb ), slide decks from weekly Zoom meetups, etc.

No description provided.

Noise Injection Techniques provides a comprehensive exploration of methods to make machine learning models more robust to real-world bad data. This repository explains and demonstrates Gaussian noise, dropout, mixup, masking, adversarial noise, and label smoothing, with intuitive explanations, theory, and practical code examples.