asmadotgh / dissect
DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
☆11Updated 9 months ago
Related projects ⓘ
Alternatives and complementary repositories for dissect
- CME: Concept-based Model Extraction☆12Updated 4 years ago
- Overlooked Factors in Concept-based Explanations: Dataset Choice, Concept Learnability, and Human Capability (CVPR 2023)☆9Updated last year
- Library implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI☆52Updated 2 years ago
- code release for the paper "On Completeness-aware Concept-Based Explanations in Deep Neural Networks"☆51Updated 2 years ago
- Implementation of the paper "A Framework for Learning Ante-hoc Explainable Models via Concepts" (CVPR 2022).☆8Updated 4 months ago
- Figures & code from the paper "Shortcut Learning in Deep Neural Networks" (Nature Machine Intelligence 2020)☆94Updated 2 years ago
- 'Robust Semantic Interpretability: Revisiting Concept Activation Vectors' Official Implementation☆11Updated 4 years ago
- ☆41Updated last year
- LISA for ICML 2022☆47Updated last year
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆45Updated 4 months ago
- Do input gradients highlight discriminative features? [NeurIPS 2021] (https://arxiv.org/abs/2102.12781)☆13Updated last year
- ☆32Updated 3 years ago
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆35Updated 2 years ago
- [ICLR'22] Self-supervised learning optimally robust representations for domain shift.☆23Updated 2 years ago
- ☆72Updated 4 years ago
- PyTorch Transformer-based Language Model Implementation of ConceptSHAP☆12Updated 4 years ago
- ☆37Updated 3 years ago
- This repository contains the implementation of Concept Activation Regions, a new framework to explain deep neural networks with human con…☆9Updated 2 years ago
- Model Patching: Closing the Subgroup Performance Gap with Data Augmentation☆42Updated 4 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆68Updated 6 months ago
- ICLR 2021, Fair Mixup: Fairness via Interpolation☆55Updated 3 years ago
- ☆37Updated 6 months ago
- [NeurIPS'22] Official Repository for Characterizing Datapoints via Second-Split Forgetting☆14Updated last year
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆35Updated 2 years ago
- ☆24Updated 3 years ago
- Code for "Generative causal explanations of black-box classifiers"☆33Updated 3 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆40Updated last year
- ☆96Updated 2 years ago
- ☆33Updated 3 years ago
- Repository for our NeurIPS 2022 paper "Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off" and our NeurIPS 2023 paper…☆52Updated this week