There are no reviews yet. Be the first to send feedback to the community and the maintainers!
sortpool2d
A new kind of pooling layer for faster and sharper convergencesalient_imagenet
Code for the ICLR 2022 paper. Salient Imagenet: How to discover spurious features in deep learning?style-transfer
style transfer code for generating stylized images using content and style loss from different layers, from different loss networks (vgg-16, vgg-19, inception-v1, inception-v2, inception-v3 trained on imagenet, inception-v3 trained on openimages, inception-v4barlow
Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extractionorthogonal-convolution
Github repo for my experiments with the orthogonal convolution idealoss-exps
Experiments with different loss functions for image classificationSOC
Code for the ICML 2021 and ICLR 2022 papers: Skew Orthogonal Convolutions, Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100CASO
code for the paper https://arxiv.org/abs/1902.00407CONV-SV
A fast and efficient way to compute a differentiable bound on the singular values of convolution layersword-language-model
word-language-model imported and modified from pytorch-examplesresnet-exps
Experiments with center loss function for image classification on resnet architectureimproved_l2_robustness
fantastic-four
Code for the ICLR paper: https://openreview.net/forum?id=JCRblSgs34Zso-robust
Code for ICML paper "Second-Order Provable Defenses against Adversarial Attacks"singlasahil14.github.io
char-rnn
data-augmentation
Code for fast data augmentationLove Open Source and this site? Check out how you can help us