ArieSeirack

DHVT

This is an official implementation of our NeurIPS 2022 paper "Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small Datasets".

Awesome-FGVC

Divide-and-Co-training

[TIP 2022] Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training. Plus, an image classification toolbox includes ResNet, Wide-ResNet, ResNeXt, ResNeSt, ResNeXSt, SENet, Shake-Shake, DenseNet, PyramidNet, and EfficientNet.

PaperReading

Paper Reading of IMCC groups.

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more