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)
☆791Updated 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)☆509Updated 6 months ago
- Pretrained bag-of-local-features neural networks☆312Updated 5 years ago
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty☆981Updated 6 months ago
- Corruption and Perturbation Robustness (ICLR 2019)☆1,040Updated 2 years ago
- Understanding Deep Networks via Extremal Perturbations and Smooth Masks☆345Updated 4 years ago
- Scaling and Benchmarking Self-Supervised Visual Representation Learning☆585Updated 3 years ago
- ☆314Updated 10 months ago
- ImageNet classifier with state-of-the-art adversarial robustness☆682Updated 5 years ago
- PyTorch re-implementation of Grad-CAM (+ vanilla/guided backpropagation, deconvnet, and occlusion sensitivity maps)☆793Updated 5 years ago
- 2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552☆548Updated 4 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 4 years ago
- Taskonomy: Disentangling Task Transfer Learning [Best Paper, CVPR2018]☆854Updated 2 years ago
- Gradient based receptive field estimation for Convolutional Neural Networks☆337Updated 5 years ago
- Visualization toolkit for neural networks in PyTorch! Demo -->☆738Updated last year
- A script that applies the AdaIN style transfer method to arbitrary datasets☆157Updated 3 years ago
- Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)☆339Updated 5 months ago
- This repository reproduces the results of the paper: "Fixing the train-test resolution discrepancy" https://arxiv.org/abs/1906.06423☆1,035Updated 3 years ago
- Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow☆1,474Updated last year
- Standardizing weights to accelerate micro-batch training☆546Updated 2 years ago
- Wide Residual Networks (WideResNets) in PyTorch☆336Updated 3 years ago
- Best CIFAR-10, CIFAR-100 results with wide-residual networks using PyTorch☆463Updated 5 years ago
- Efficient Learning of Augmentation Policy Schedules☆505Updated 5 years ago
- Full-gradient saliency maps☆207Updated last year
- Code for Noisy Student Training. https://arxiv.org/abs/1911.04252☆755Updated 3 years ago
- Official PyTorch implementation of Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion (CVPR 2020)☆490Updated 2 years ago
- Official Pytorch implementation of CutMix regularizer☆1,226Updated 4 years ago
- A simple and effective method for detecting out-of-distribution images in neural networks.☆536Updated 3 years ago
- mixup: Beyond Empirical Risk Minimization☆1,171Updated 3 years ago
- Unofficial PyTorch Reimplementation of RandAugment.☆631Updated last year
- Public repo for Augmented Multiscale Deep InfoMax representation learning☆401Updated 4 years ago