Trustworthy-ML-Lab / Label-free-CBMLinks
[ICLR 23] A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled concept data
☆128Updated last year
Alternatives and similar repositories for Label-free-CBM
Users that are interested in Label-free-CBM are comparing it to the libraries listed below
Sorting:
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023☆89Updated last year
- CVPR 2023: Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification☆105Updated last year
- [ICLR 23 spotlight] An automatic and efficient tool to describe functionalities of individual neurons in DNNs☆59Updated 2 years ago
- Repository for our NeurIPS 2022 paper "Concept Embedding Models", our NeurIPS 2023 paper "Learning to Receive Help", and our ICML 2025 pa…☆71Updated 2 months ago
- Concept Bottleneck Models, ICML 2020☆234Updated 2 years ago
- Implementation of Concept-level Debugging of Part-Prototype Networks☆12Updated 2 years ago
- [ICML 2023] Change is Hard: A Closer Look at Subpopulation Shift☆111Updated 2 years ago
- [NeurIPS 24] A new training and evaluation framework for learning interpretable deep vision models and benchmarking different interpretab…☆27Updated 6 months ago
- ☆71Updated 2 years ago
- ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition☆40Updated 3 years ago
- PyTorch implementation of our CVPR2023 paper "OpenMix: Exploring Out-of-Distribution samples for Misclassification Detection"☆27Updated 2 years ago
- Code for Continuously Changing Corruptions (CCC) benchmark + evaluation☆40Updated last year
- [ICLR'24] Official code for "C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion"☆22Updated last year
- [ICML 2023] On Pitfalls of Test-Time Adaptation☆124Updated last year
- This is the official implementation of the Concept Discovery Models paper.☆15Updated 2 years ago
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆50Updated last year
- SpuCo is a Python package developed to further research to address spurious correlations.☆24Updated 11 months ago
- ☆46Updated last year
- [NeurIPS '24] Frustratingly easy Test-Time Adaptation of VLMs!!☆60Updated 9 months ago
- ☆23Updated last year
- Code for the paper Visual Explanations of Image–Text Representations via Multi-Modal Information Bottleneck Attribution☆64Updated last year
- [CVPR 2022] HINT: Hierarchical Neuron Concept Explainer☆20Updated 2 years ago
- Test-Time Adaptation via Conjugate Pseudo-Labels☆43Updated 2 years ago
- Code for Finetune like you pretrain: Improved finetuning of zero-shot vision models☆104Updated 2 years ago
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆53Updated last year
- ☆29Updated last year
- PyTorch implementation of MCM (Delving into out-of-distribution detection with vision-language representations), NeurIPS 2022☆92Updated last year
- Learning Bottleneck Concepts in Image Classification (CVPR 2023)☆41Updated 2 years ago
- (ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation☆42Updated last month
- A collection of model transferability estimation methods.☆30Updated last year