Trustworthy-ML-Lab / CLIP-dissectLinks
[ICLR 23 spotlight] An automatic and efficient tool to describe functionalities of individual neurons in DNNs
☆52Updated last year
Alternatives and similar repositories for CLIP-dissect
Users that are interested in CLIP-dissect are comparing it to the libraries listed below
Sorting:
- [ICLR 23] A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled c…☆103Updated last year
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023☆78Updated last year
- [NeurIPS 24] A new training and evaluation framework for learning interpretable deep vision models and benchmarking different interpretab…☆18Updated 3 weeks ago
- Official code for "Can We Talk Models Into Seeing the World Differently?" (ICLR 2025).☆25Updated 5 months ago
- SpuCo is a Python package developed to further research to address spurious correlations.☆24Updated 5 months ago
- CVPR 2023: Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification☆91Updated last year
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆48Updated 11 months ago
- Official Code Release for "Diagnosing and Rectifying Vision Models using Language" (ICLR 2023)☆34Updated 2 years ago
- Code for Continuously Changing Corruptions (CCC) benchmark + evaluation☆35Updated 10 months ago
- [CVPR 2022] HINT: Hierarchical Neuron Concept Explainer☆20Updated 2 years ago
- What do we learn from inverting CLIP models?☆55Updated last year
- Official repository for the ICCV 2023 paper: "Waffling around for Performance: Visual Classification with Random Words and Broad Concepts…☆57Updated last year
- 👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)☆65Updated last year
- Official codebase for the NeurIPS 2023 paper: Towards Last-layer Retraining for Group Robustness with Fewer Annotations. https://arxiv.or…☆11Updated last year
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet☆32Updated last year
- ☆57Updated 7 months ago
- ☆22Updated last year
- Sparse Linear Concept Embeddings☆105Updated 2 months ago
- Official code for the paper "Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?" (ICLR 2024)☆10Updated 10 months ago
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆45Updated 7 months ago
- Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"☆39Updated 7 months ago
- [NeurIPS '24] Frustratingly easy Test-Time Adaptation of VLMs!!☆47Updated 3 months ago
- ☆39Updated last year
- Natural Language Descriptions of Deep Visual Features, ICLR 2022☆65Updated last year
- Test-Time Adaptation via Conjugate Pseudo-Labels☆41Updated 2 years ago
- ☆13Updated 2 years ago
- ☆107Updated last year
- Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations" (ICLR '25)☆75Updated 3 weeks ago
- Code for the CCE algorithm proposed in "Towards Compositionality in Concept Learning" at ICML 2024.☆15Updated last year
- The example of correspondence between fine classes and superclass (coarse class) in ImageNet.☆12Updated 6 months ago