bethgelab / model-vs-human
Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)
☆339Updated 5 months ago
Alternatives and similar repositories for model-vs-human:
Users that are interested in model-vs-human are comparing it to the libraries listed below
- ☆314Updated 10 months ago
- ImageNet-R(endition) and DeepAugment (ICCV 2021)☆259Updated 3 years ago
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆203Updated last year
- ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."☆117Updated last year
- A new test set for ImageNet☆245Updated last year
- 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
- Understanding Training Dynamics of Deep ReLU Networks☆284Updated last week
- Train ImageNet *fast* in 500 lines of code with FFCV☆136Updated 8 months ago
- Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)☆509Updated 6 months ago
- A LARS implementation in PyTorch☆338Updated 4 years ago
- A PyTorch converter for SimCLR checkpoints☆107Updated 4 years ago
- Reproduce CKA: Similarity of Neural Network Representations Revisited☆297Updated 4 years ago
- Compare neural networks by their feature similarity☆349Updated last year
- ☆181Updated last year
- Official code for the CVPR 2021 paper "How Well Do Self-Supervised Models Transfer?"☆181Updated last year
- Full-gradient saliency maps☆207Updated last year
- EsViT: Efficient self-supervised Vision Transformers☆409Updated last year
- Robustness and adaptation of ImageNet scale models. Pre-Release, stay tuned for updates.☆132Updated last year
- Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch☆316Updated last year
- PyTorch implementation of SimCLR: supports multi-GPU training and closely reproduces results☆197Updated 9 months ago
- ☆140Updated 4 years ago
- PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures (CVPR 2022)☆101Updated 2 years ago
- Corruption and Perturbation Robustness (ICLR 2019)☆1,040Updated 2 years ago
- Implementation of Barlow Twins paper☆99Updated 2 years ago
- Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improv…☆791Updated last year
- ImageNet-Sketch data set for evaluating model's ability in learning (out-of-domain) semantics at ImageNet scale☆209Updated 2 years ago
- (ICLR 2022 Spotlight) Official PyTorch implementation of "How Do Vision Transformers Work?"☆808Updated 2 years ago
- Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"☆419Updated 2 years ago
- Original dataset release for CIFAR-10H☆82Updated 4 years ago
- [NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)☆176Updated 3 years ago