eth-sri / fnf
☆16Updated 2 years ago
Related projects: ⓘ
- ☆37Updated 3 years ago
- Source code of "Hold me tight! Influence of discriminative features on deep network boundaries"☆22Updated 2 years ago
- ☆17Updated last year
- ☆32Updated 11 months ago
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆35Updated 2 years ago
- Code for ICLR 2022 Paper, "Controlling Directions Orthogonal to a Classifier"☆34Updated last year
- This code reproduces the results of the paper, "Measuring Data Leakage in Machine-Learning Models with Fisher Information"☆48Updated 3 years ago
- ☆25Updated 4 years ago
- Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"☆24Updated 2 years ago
- This is the official implementation of ClusTR: Clustering Training for Robustness paper.☆20Updated 2 years ago
- ☆34Updated last month
- Pytorch implementation for "The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction"☆33Updated 2 years ago
- ☆23Updated 3 years ago
- ☆40Updated last year
- Code for the ICLR 2020 Paper, "A Theory of Usable Information under Computational Constraints"☆22Updated 4 years ago
- Developing adversarial examples and showing their semantic generalization for the OpenAI CLIP model (https://github.com/openai/CLIP)☆26Updated 3 years ago
- Improving Transformation Invariance in Contrastive Representation Learning☆13Updated 3 years ago
- ICLR 2021, Fair Mixup: Fairness via Interpolation☆55Updated 3 years ago
- ☆55Updated 4 years ago
- DiWA: Diverse Weight Averaging for Out-of-Distribution Generalization☆27Updated last year
- ☆40Updated last year
- ICML 2020, Estimating Generalization under Distribution Shifts via Domain-Invariant Representations☆21Updated 4 years ago
- Learning perturbation sets for robust machine learning☆64Updated 3 years ago
- Model Patching: Closing the Subgroup Performance Gap with Data Augmentation☆42Updated 3 years ago
- Code for the paper "Semi-Conditional Normalizing Flows for Semi-Supervised Learning"☆10Updated 4 years ago
- Guarantees on the behavior of neural networks don't always have to come at the cost of performance.☆28Updated last year
- SGD with large step sizes learns sparse features [ICML 2023]☆31Updated last year
- Geometric Certifications of Neural Nets☆41Updated last year
- Fine-grained ImageNet annotations☆29Updated 4 years ago
- ☆18Updated 2 years ago