AlexMeinke / Provable-OOD-Detection
Guarantees on the behavior of neural networks don't always have to come at the cost of performance.
☆28Updated last year
Related projects: ⓘ
- A way to achieve uniform confidence far away from the training data.☆36Updated 3 years ago
- ☆34Updated 3 years ago
- Active and Sample-Efficient Model Evaluation☆24Updated 3 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆39Updated 10 months ago
- ☆32Updated 11 months ago
- Code for "The Intrinsic Dimension of Images and Its Impact on Learning" - ICLR 2021 Spotlight https://openreview.net/forum?id=XJk19XzGq2J☆63Updated 5 months ago
- Geometric Certifications of Neural Nets☆41Updated last year
- ☆33Updated 3 years ago
- Learning perturbation sets for robust machine learning☆64Updated 3 years ago
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆35Updated 2 years ago
- Code for the paper "Semi-Conditional Normalizing Flows for Semi-Supervised Learning"☆10Updated 4 years ago
- Rethinking Bias-Variance Trade-off for Generalization of Neural Networks☆49Updated 3 years ago
- Implementation of Methods Proposed in Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks (NeurIPS 2019)☆33Updated 4 years ago
- ☆55Updated 4 years ago
- PyTorch implementation of JEM++: Improved Techniques for Training JEM☆13Updated last year
- Last-layer Laplace approximation code examples☆78Updated 2 years ago
- ☆25Updated 4 years ago
- Pre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)☆99Updated 2 years ago
- ☆37Updated 3 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆59Updated 3 years ago
- Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks☆13Updated 2 years ago
- ☆11Updated 2 years ago
- CIFAR-5m dataset☆39Updated 3 years ago
- ☆37Updated 5 years ago
- CVPR'19 experiments with (on-manifold) adversarial examples.☆43Updated 4 years ago
- SGD with large step sizes learns sparse features [ICML 2023]☆31Updated last year
- Source code of "Hold me tight! Influence of discriminative features on deep network boundaries"☆22Updated 2 years ago
- ☆31Updated 3 years ago
- Code for "Bridging the Gap between f-GANs and Wasserstein GANs", ICML 2020☆14Updated 4 years ago
- Codes for the paper "Optimizing Mode Connectivity via Neuron Alignment" from NeurIPS 2020.☆15Updated 3 years ago