bethgelab / model-vs-human
Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)
☆336Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for model-vs-human
- ☆311Updated 7 months ago
- ImageNet-R(endition) and DeepAugment (ICCV 2021)☆254Updated 3 years ago
- Train ImageNet *fast* in 500 lines of code with FFCV☆136Updated 5 months ago
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆203Updated last year
- Reproduce CKA: Similarity of Neural Network Representations Revisited☆287Updated 4 years ago
- Compare neural networks by their feature similarity☆342Updated last year
- A new test set for ImageNet☆240Updated last year
- ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."☆116Updated last year
- Full-gradient saliency maps☆203Updated last year
- A PyTorch converter for SimCLR checkpoints☆106Updated 3 years ago
- A LARS implementation in PyTorch☆335Updated 4 years ago
- Robustness and adaptation of ImageNet scale models. Pre-Release, stay tuned for updates.☆129Updated last year
- A script that applies the AdaIN style transfer method to arbitrary datasets☆155Updated 3 years ago
- Understanding Training Dynamics of Deep ReLU Networks☆278Updated 2 weeks ago
- ☆138Updated 4 years ago
- ImageNet-Sketch data set for evaluating model's ability in learning (out-of-domain) semantics at ImageNet scale☆201Updated 2 years ago
- Corruption and Perturbation Robustness (ICLR 2019)☆1,019Updated 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…☆301Updated 3 years ago
- ☆177Updated last year
- Implementation of Barlow Twins paper☆99Updated 2 years ago
- Original dataset release for CIFAR-10H☆80Updated 4 years ago
- Official repository for "Intriguing Properties of Vision Transformers" (NeurIPS 2021--Spotlight)☆176Updated 2 years ago
- Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)☆506Updated 3 months ago
- Official code for the CVPR 2021 paper "How Well Do Self-Supervised Models Transfer?"☆181Updated last year
- EsViT: Efficient self-supervised Vision Transformers☆408Updated last year
- Implementation of Slot Attention from GoogleAI☆394Updated 2 months ago
- Understanding Deep Networks via Extremal Perturbations and Smooth Masks☆344Updated 4 years ago
- Pretrained SimCLRv2 models in Pytorch☆104Updated 4 years ago
- Drop-in replacement for any ResNet with a significantly reduced memory footprint and better representation capabilities☆208Updated 6 months ago
- PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures (CVPR 2022)☆100Updated 2 years ago