This repository contains the implementation of Concept Activation Regions, a new framework to explain deep neural networks with human concepts. For more details, please read our NeurIPS 2022 paper: 'Concept Activation Regions: a Generalized Framework for Concept-Based Explanations.
☆16Oct 7, 2022Updated 3 years ago
Alternatives and similar repositories for CARs
Users that are interested in CARs are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆12Oct 23, 2022Updated 3 years ago
- Improving neural network representations using human similarity judgments☆13Nov 22, 2024Updated last year
- DISSECT: Disentangled Simultaneous Explanations via Concept Traversals☆12Feb 5, 2024Updated 2 years ago
- Code for ECCV 2022 paper "DICE: Leveraging Sparsification for Out-of-Distribution Detection"☆41Sep 28, 2022Updated 3 years ago
- Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation☆45Feb 27, 2023Updated 3 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Implementation of Concept-level Debugging of Part-Prototype Networks☆12May 9, 2023Updated 2 years ago
- ☆96Oct 27, 2022Updated 3 years ago
- ☆28Nov 28, 2024Updated last year
- Code for the paper "Model Agnostic Interpretability for Multiple Instance Learning".☆13Jan 28, 2022Updated 4 years ago
- Code release for paper Extremely Simple Activation Shaping for Out-of-Distribution Detection☆55Aug 30, 2024Updated last year
- Code for paper "Principled feature attribution for unsupervised gene expression analysis"☆12Mar 7, 2023Updated 3 years ago
- Official codebase for the paper "Provable concept learning for interpretable predictions using variational inference".☆15Apr 4, 2022Updated 3 years ago
- Implementation for <Robust Weight Perturbation for Adversarial Training> in IJCAI'22.☆16Jul 1, 2022Updated 3 years ago
- Source code for the paper "Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness"☆25Feb 12, 2020Updated 6 years ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Feature Importance Analysis of Models☆11Mar 23, 2022Updated 4 years ago
- On the effectiveness of adversarial training against common corruptions [UAI 2022]☆30May 16, 2022Updated 3 years ago
- ☆27Jan 25, 2024Updated 2 years ago
- PyTorch implementation of POEM (Out-of-distribution detection with posterior sampling), ICML 2022☆28May 6, 2023Updated 2 years ago
- ☆16Oct 23, 2019Updated 6 years ago
- ☆41Nov 30, 2023Updated 2 years ago
- Implementation of the paper "Improving the Accuracy-Robustness Trade-off of Classifiers via Adaptive Smoothing".☆10Feb 6, 2024Updated 2 years ago
- ☆35Sep 23, 2022Updated 3 years ago
- Repository for research works and resources related to model reprogramming <https://arxiv.org/abs/2202.10629>☆64Sep 17, 2025Updated 6 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆36Jul 14, 2022Updated 3 years ago
- Code for "Generative causal explanations of black-box classifiers"☆36Jan 15, 2021Updated 5 years ago
- Official Code for the ACCV 2022 paper Diffusion Models for Counterfactual Explanations☆29Mar 12, 2025Updated last year
- ModelDiff: A Framework for Comparing Learning Algorithms☆58Aug 15, 2023Updated 2 years ago
- Monitor parameter and gradient statistics during neural network training with Chainer☆13Jan 24, 2017Updated 9 years ago
- ☆11Mar 20, 2026Updated last week
- Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with Invertible Neural Networks☆59Dec 18, 2020Updated 5 years ago
- Original dataset release for CIFAR-10H☆83Updated this week
- Code to study the generalisability of benchmark models on non-stationary EHRs.☆15Aug 7, 2019Updated 6 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆10Oct 14, 2023Updated 2 years ago
- 'Robust Semantic Interpretability: Revisiting Concept Activation Vectors' Official Implementation☆11Jul 15, 2020Updated 5 years ago
- A method to generate counterfactuals☆12Feb 24, 2026Updated last month
- Code for [Re] On the Reproducibility of Post-Hoc Concept Bottleneck Models.☆13Nov 27, 2024Updated last year
- ☆13Nov 29, 2021Updated 4 years ago
- NPFL129 repository☆44Jan 9, 2026Updated 2 months ago
- The codes of our paper "EasyInv: Toward Fast and Better DDIM Inversion"☆14Jun 1, 2025Updated 9 months ago