rgeirhos / texture-vs-shapeLinks
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)
☆809Updated 2 years ago
Alternatives and similar repositories for texture-vs-shape
Users that are interested in texture-vs-shape are comparing it to the libraries listed below
Sorting:
- Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)☆524Updated this week
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty☆988Updated 7 months ago
- Scaling and Benchmarking Self-Supervised Visual Representation Learning☆587Updated 4 years ago
- Understanding Deep Networks via Extremal Perturbations and Smooth Masks☆348Updated 5 years ago
- Pretrained bag-of-local-features neural networks☆315Updated 6 years ago
- Corruption and Perturbation Robustness (ICLR 2019)☆1,127Updated 3 years ago
- ☆525Updated 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…☆306Updated 5 years ago
- Standardizing weights to accelerate micro-batch training☆549Updated 3 years ago
- A simple and effective method for detecting out-of-distribution images in neural networks.☆539Updated 4 years ago
- ImageNet classifier with state-of-the-art adversarial robustness☆687Updated 6 years ago
- A script that applies the AdaIN style transfer method to arbitrary datasets☆165Updated 4 years ago
- Visualization toolkit for neural networks in PyTorch! Demo -->☆743Updated 2 years ago
- Light version of Network Dissection for Quantifying Interpretability of Networks☆221Updated 6 years ago
- 2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552☆555Updated 5 years ago
- Full-gradient saliency maps☆212Updated 2 years ago
- PyTorch re-implementation of Grad-CAM (+ vanilla/guided backpropagation, deconvnet, and occlusion sensitivity maps)☆801Updated 5 years ago
- Best CIFAR-10, CIFAR-100 results with wide-residual networks using PyTorch☆478Updated 6 years ago
- ☆340Updated 5 months ago
- pip install antialiased-cnns to improve stability and accuracy☆1,679Updated last year
- Unofficial PyTorch Reimplementation of RandAugment.☆639Updated 2 years ago
- Taskonomy: Disentangling Task Transfer Learning [Best Paper, CVPR2018]☆872Updated 3 years ago
- Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow☆1,495Updated 2 years ago
- Wide Residual Networks (WideResNets) in PyTorch☆347Updated 4 years ago
- Pytorch implementation of convolutional neural network adversarial attack techniques☆364Updated 7 years ago
- A new test set for ImageNet☆261Updated 2 years ago
- mixup: Beyond Empirical Risk Minimization☆1,198Updated 4 years ago
- Official PyTorch implementation of Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion (CVPR 2020)☆518Updated 2 years ago
- This repository reproduces the results of the paper: "Fixing the train-test resolution discrepancy" https://arxiv.org/abs/1906.06423☆1,044Updated 4 years ago
- Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)☆358Updated 9 months ago