Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem [CVPR 2019, oral]
☆185Jul 14, 2019Updated 7 years ago
Alternatives and similar repositories for relu_networks_overconfident
Users that are interested in relu_networks_overconfident are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A way to achieve uniform confidence far away from the training data.☆38Apr 16, 2021Updated 5 years ago
- ☆12Feb 19, 2025Updated last year
- Geometric Certifications of Neural Nets☆42Nov 22, 2022Updated 3 years ago
- ☆18Dec 4, 2021Updated 4 years ago
- Provable Robustness of ReLU networks via Maximization of Linear Regions [AISTATS 2019]☆31Jul 15, 2020Updated 6 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Code implementing the experiments described in the NeurIPS 2018 paper "With Friends Like These, Who Needs Adversaries?".☆13Sep 11, 2020Updated 6 years ago
- A Closer Look at Accuracy vs. Robustness☆89May 17, 2021Updated 5 years ago
- Code for the paper "Adversarial Training and Robustness for Multiple Perturbations", NeurIPS 2019☆46Dec 8, 2022Updated 3 years ago
- Benchmark for LP-relaxed robustness verification of ReLU-networks☆42Apr 24, 2019Updated 7 years ago
- ☆25May 20, 2020Updated 6 years ago
- Code for the paper "A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks".☆356Aug 13, 2019Updated 7 years ago
- ☆23Jun 15, 2022Updated 4 years ago
- Source code for the paper "Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness"☆25Feb 12, 2020Updated 6 years ago
- Code for ECCV 2022 paper "DICE: Leveraging Sparsification for Out-of-Distribution Detection"☆42Sep 28, 2022Updated 4 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation [NeurIPS 2017]☆18Apr 8, 2018Updated 8 years ago
- code for model-targeted poisoning☆12Oct 3, 2023Updated 3 years ago
- [ICML'20] Multi Steepest Descent (MSD) for robustness against the union of multiple perturbation models.☆25Jul 25, 2024Updated 2 years ago
- Interval attacks (adversarial ML)☆21Jun 17, 2019Updated 7 years ago
- Unrestricted adversarial images via interpretable color transformations (TIFS 2023 & BMVC 2020)☆32Apr 25, 2023Updated 3 years ago
- Code for FAB-attack☆35Jul 10, 2020Updated 6 years ago
- [AAAI'20][ICML'19 AutoML] This repository is the implementation of "InstaNAS: Instance-aware Neural Architecture Search"☆93May 6, 2021Updated 5 years ago
- Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.☆48Oct 3, 2023Updated 3 years ago
- Deep Anomaly Detection with Outlier Exposure (ICLR 2019)☆572Oct 9, 2021Updated 5 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- The Official Implementation of the ICCV-2021 Paper: Semantically Coherent Out-of-Distribution Detection.☆70Mar 21, 2022Updated 4 years ago
- Pytorch implementation for "Large-Scale Long-Tailed Recognition in an Open World" (CVPR 2019 ORAL)☆873Jul 16, 2022Updated 4 years ago
- Robustness for Non-Parametric Classification: A Generic Attack and Defense☆18Nov 21, 2022Updated 3 years ago
- Code for "Interpretable Image Recognition with Hierarchical Prototypes"☆19Nov 1, 2019Updated 6 years ago
- Guarantees on the behavior of neural networks don't always have to come at the cost of performance.☆30Oct 12, 2022Updated 4 years ago
- SGD with large step sizes learns sparse features [ICML 2023]☆35Apr 24, 2023Updated 3 years ago
- Code for the CVPR 2019 article "Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses"☆137Nov 25, 2020Updated 5 years ago
- Code release for paper "A Modulation Module for Multi-task Learning with Applications in Image Retrieval"☆31Dec 8, 2018Updated 7 years ago
- Understanding and Improving Fast Adversarial Training [NeurIPS 2020]☆97Sep 23, 2021Updated 5 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Implementation of Hardness-Aware Deep Metric Learning (CVPR 2019 Oral) in Tensorflow.☆150Apr 3, 2020Updated 6 years ago
- ImageNet classifier with state-of-the-art adversarial robustness☆682Dec 31, 2019Updated 6 years ago
- On the Importance of Gradients for Detecting Distributional Shifts in the Wild☆56Aug 3, 2022Updated 4 years ago
- ☆14Sep 7, 2022Updated 4 years ago
- ☆41Dec 8, 2022Updated 3 years ago
- ☆13Jun 23, 2022Updated 4 years ago
- Noise-Tolerant Paradigm for Training Face Recognition CNNs [Official, CVPR 2019]☆136Mar 27, 2019Updated 7 years ago