This repo implements a ViT based model with Mixup Data Augmentation method. All the models including ViT are implemented from scratch using tensorflow

Python codes to implement DeMix, a DETR assisted CutMix method for image data augmentation

HTCLite implementation using PyTorch (supports MOSAIC/MixUp and RandomAugment)

Classification using Vision Transformers (ViT) and MixUp Augmentation

Model Compression using Knowledge Distillation

Image Classification Using Swin Transformer With RandAugment, CutMix, and MixUp

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

A new regularization technique by encountering samples through exponential smoothing

Faster large mini-batch distributed training w/o. squeezing devices

High Accuracy ResNet Model under 5 Million parameters.

A repository to host recent papers on Manifold Mixup.

Deep learning solution for Cassava Leaf Disease Classification, a Kaggle's Research Code Competition using Tensorflow.

Bronze medal solution for the "Bengali.AI Handwritten Grapheme Classification" Kaggle competition

DualDet implementation using PyTorch

To evaluate the performance of each regularization method (cutout, mixup, and self-supervised rotation predictor), we apply it to the CIFAR-10 dataset using a deep residual network with a depth of 20 (ResNet20)

用一篇文章混淆一篇文章(比如公众号)

a lightweight project for classification and bag of tricks are employed for better performance