singlasahil14 / SOCLinks
Code for the ICML 2021 and ICLR 2022 papers: Skew Orthogonal Convolutions, Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100
☆18Updated 3 years ago
Alternatives and similar repositories for SOC
Users that are interested in SOC are comparing it to the libraries listed below
Sorting:
- Official Implementation of Convolutional Normalization: Improving Robustness and Training for Deep Neural Networks☆30Updated 3 years ago
- Implementations of orthogonal and semi-orthogonal convolutions in the Fourier domain with applications to adversarial robustness☆48Updated 4 years ago
- Implementations of the algorithms described in the paper: On the Convergence Theory for Hessian-Free Bilevel Algorithms.☆10Updated last year
- ☆58Updated 3 years ago
- Code for paper "Orthogonal Convolutional Neural Networks".☆118Updated 4 years ago
- Robust Optimal Transport code☆44Updated 3 years ago
- ☆19Updated 2 years ago
- [ICLR 2022] "Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice" by Peihao Wang, Wen…☆83Updated 2 years ago
- Code for ICLR 2022 Paper, "Controlling Directions Orthogonal to a Classifier"☆35Updated 2 years ago
- ☆41Updated 4 years ago
- ☆12Updated 3 years ago
- PyTorch Implementation of MIMO (ICLR 2021)☆16Updated 3 years ago
- NeurIPS 2021, Code for Measuring Generalization with Optimal Transport☆28Updated 4 years ago
- ☆20Updated 6 years ago
- Github code for the paper Maximum Class Separation as Inductive Bias in One Matrix. Arxiv link: https://arxiv.org/abs/2206.08704☆30Updated 2 years ago
- Codebase for the paper "Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning"☆17Updated 4 years ago
- PyTorch implementation of the paper "Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization" (ICLR 2021)☆33Updated 3 years ago
- Code repository for the paper "Group Equivariant Stand-Alone Self Attention For Vision" published at ICLR 2021. https://openreview.net/fo…☆28Updated 4 years ago
- Code for the paper "Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification" (2020)☆43Updated last year
- Prospect Pruning: Finding Trainable Weights at Initialization Using Meta-Gradients☆32Updated 3 years ago
- We investigated corruption robustness across different architectures including Convolutional Neural Networks, Vision Transformers, and th…☆16Updated 4 years ago
- Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable ? (ICML 2021)☆28Updated 3 years ago
- Code for CVPR2021 paper: MOOD: Multi-level Out-of-distribution Detection☆38Updated 2 years ago
- Learning Representations that Support Robust Transfer of Predictors☆20Updated 4 years ago
- This is the official implementation of the ICML 2023 paper - Can Forward Gradient Match Backpropagation ?☆13Updated 2 years ago
- Minimum viable code for the Decodable Information Bottleneck paper. Pytorch Implementation.☆11Updated 5 years ago
- Anonymized code for Igeood: An Information Geometry Approach to Out-of-Distribution Detection☆12Updated 4 years ago
- Efficient solution to the initialization selection of DNNs in transfer learning using duality diagrams as a similarity measure framework.☆10Updated 5 years ago
- Implicit networks can be trained efficiently and simply by using Jacobian-free Backprop (JFB).☆41Updated 4 years ago
- This is the pytorch re-implementation of the IterNorm☆41Updated 6 years ago