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)
☆805Updated 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)☆519Updated 3 months ago
- Understanding Deep Networks via Extremal Perturbations and Smooth Masks☆347Updated 5 years ago
- Scaling and Benchmarking Self-Supervised Visual Representation Learning☆587Updated 3 years ago
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty☆988Updated 4 months ago
- Pretrained bag-of-local-features neural networks☆314Updated 6 years ago
- Corruption and Perturbation Robustness (ICLR 2019)☆1,100Updated 3 years ago
- PyTorch re-implementation of Grad-CAM (+ vanilla/guided backpropagation, deconvnet, and occlusion sensitivity maps)☆799Updated 5 years ago
- A script that applies the AdaIN style transfer method to arbitrary datasets☆161Updated 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☆218Updated 6 years ago
- ImageNet classifier with state-of-the-art adversarial robustness☆685Updated 5 years ago
- ☆520Updated last year
- Full-gradient saliency maps☆212Updated 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…☆304Updated 4 years ago
- pip install antialiased-cnns to improve stability and accuracy☆1,679Updated last year
- Best CIFAR-10, CIFAR-100 results with wide-residual networks using PyTorch☆470Updated 5 years ago
- Official Implementation of 'Fast AutoAugment' in PyTorch.☆1,610Updated 4 years ago
- Standardizing weights to accelerate micro-batch training☆550Updated 3 years ago
- 2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552☆553Updated 5 years ago
- Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow☆1,489Updated 2 years ago
- This repository reproduces the results of the paper: "Fixing the train-test resolution discrepancy" https://arxiv.org/abs/1906.06423☆1,045Updated 4 years ago
- ☆334Updated 2 months ago
- Pytorch implementation of convolutional neural network adversarial attack techniques☆360Updated 6 years ago
- Taskonomy: Disentangling Task Transfer Learning [Best Paper, CVPR2018]☆870Updated 2 years ago
- A simple and effective method for detecting out-of-distribution images in neural networks.☆538Updated 3 years ago
- Unofficial PyTorch Reimplementation of RandAugment.☆636Updated 2 years ago
- mixup: Beyond Empirical Risk Minimization☆1,192Updated 3 years ago
- A new test set for ImageNet☆256Updated 2 years ago
- Official Pytorch implementation of CutMix regularizer☆1,246Updated 5 years ago
- A Pytorch-Lightning implementation of self-supervised algorithms☆544Updated 3 years ago