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)
☆796Updated last year
Alternatives and similar repositories for texture-vs-shape:
Users that are interested in texture-vs-shape are comparing it to the libraries listed below
- Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)☆513Updated 8 months ago
- A script that applies the AdaIN style transfer method to arbitrary datasets☆159Updated 3 years ago
- Corruption and Perturbation Robustness (ICLR 2019)☆1,060Updated 2 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…☆303Updated 4 years ago
- ImageNet classifier with state-of-the-art adversarial robustness☆682Updated 5 years ago
- Scaling and Benchmarking Self-Supervised Visual Representation Learning☆586Updated 3 years ago
- Standardizing weights to accelerate micro-batch training☆547Updated 3 years ago
- Pretrained bag-of-local-features neural networks☆312Updated 5 years ago
- PyTorch re-implementation of Grad-CAM (+ vanilla/guided backpropagation, deconvnet, and occlusion sensitivity maps)☆796Updated 5 years ago
- Understanding Deep Networks via Extremal Perturbations and Smooth Masks☆345Updated 4 years ago
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty☆984Updated last week
- Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)☆343Updated 7 months ago
- Visualization toolkit for neural networks in PyTorch! Demo -->☆738Updated last year
- Gradient based receptive field estimation for Convolutional Neural Networks☆338Updated 5 years ago
- Python package to corrupt arbitrary images.☆426Updated 5 months ago
- Official Implementation of 'Fast AutoAugment' in PyTorch.☆1,600Updated 3 years ago
- A Harder ImageNet Test Set (CVPR 2021)☆602Updated last year
- Taskonomy: Disentangling Task Transfer Learning [Best Paper, CVPR2018]☆859Updated 2 years ago
- This repository reproduces the results of the paper: "Fixing the train-test resolution discrepancy" https://arxiv.org/abs/1906.06423☆1,040Updated 3 years ago
- 2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552☆551Updated 5 years ago
- pip install antialiased-cnns to improve stability and accuracy☆1,668Updated 11 months ago
- mixup: Beyond Empirical Risk Minimization☆1,177Updated 3 years ago
- A simple and effective method for detecting out-of-distribution images in neural networks.☆536Updated 3 years ago
- Light version of Network Dissection for Quantifying Interpretability of Networks☆216Updated 5 years ago
- Wide Residual Networks (WideResNets) in PyTorch☆336Updated 3 years ago
- Full-gradient saliency maps☆208Updated 2 years ago
- ☆320Updated 2 weeks ago
- ☆518Updated last year
- Best CIFAR-10, CIFAR-100 results with wide-residual networks using PyTorch☆467Updated 5 years ago
- Pytorch implementation for "Large-Scale Long-Tailed Recognition in an Open World" (CVPR 2019 ORAL)☆858Updated 2 years ago