rgeirhos / texture-vs-shape
Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)
☆789Updated last year
Related projects ⓘ
Alternatives and complementary repositories for texture-vs-shape
- Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)☆506Updated 3 months ago
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty☆978Updated 3 months ago
- Understanding Deep Networks via Extremal Perturbations and Smooth Masks☆344Updated 4 years ago
- PyTorch re-implementation of Grad-CAM (+ vanilla/guided backpropagation, deconvnet, and occlusion sensitivity maps)☆787Updated 4 years ago
- Scaling and Benchmarking Self-Supervised Visual Representation Learning☆587Updated 3 years ago
- Pretrained bag-of-local-features neural networks☆312Updated 5 years ago
- Corruption and Perturbation Robustness (ICLR 2019)☆1,024Updated 2 years ago
- A script that applies the AdaIN style transfer method to arbitrary datasets☆155Updated 3 years ago
- Code for the Proceedings of the National Academy of Sciences 2020 article, "Understanding the Role of Individual Units in a Deep Neural N…☆299Updated 3 years ago
- Standardizing weights to accelerate micro-batch training☆546Updated 2 years ago
- Visualization toolkit for neural networks in PyTorch! Demo -->☆735Updated last year
- Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow☆1,468Updated last year
- A Simple pytorch implementation of GradCAM and GradCAM++☆359Updated 5 years ago
- Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)☆336Updated 3 months ago
- This repository reproduces the results of the paper: "Fixing the train-test resolution discrepancy" https://arxiv.org/abs/1906.06423☆1,033Updated 3 years ago
- Official Implementation of 'Fast AutoAugment' in PyTorch.☆1,596Updated 3 years ago
- ImageNet classifier with state-of-the-art adversarial robustness☆678Updated 4 years ago
- Official Pytorch implementation of CutMix regularizer☆1,221Updated 4 years ago
- Gradient based receptive field estimation for Convolutional Neural Networks☆336Updated 4 years ago
- pip install antialiased-cnns to improve stability and accuracy☆1,657Updated 7 months ago
- Full-gradient saliency maps☆203Updated last year
- Unofficial PyTorch Reimplementation of RandAugment.☆630Updated last year
- Best CIFAR-10, CIFAR-100 results with wide-residual networks using PyTorch☆461Updated 4 years ago
- A simple and effective method for detecting out-of-distribution images in neural networks.☆531Updated 3 years ago
- A Harder ImageNet Test Set (CVPR 2021)☆595Updated 8 months ago
- ☆514Updated last year
- mixup: Beyond Empirical Risk Minimization☆1,168Updated 3 years ago
- 2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552☆544Updated 4 years ago
- ☆311Updated 8 months ago
- Wide Residual Networks (WideResNets) in PyTorch☆334Updated 3 years ago