Trustworthy-ML-Lab / CLIP-dissect
An automatic and efficient tool to describe functionalities of individual neurons in DNNs
☆38Updated 10 months ago
Related projects: ⓘ
- A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled concept dat…☆69Updated 5 months ago
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023☆63Updated 4 months ago
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆41Updated 2 months ago
- [CVPR 2022] HINT: Hierarchical Neuron Concept Explainer☆20Updated last year
- CVPR 2023: Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification☆68Updated 3 months ago
- Official repository for the ICCV 2023 paper: "Waffling around for Performance: Visual Classification with Random Words and Broad Concepts…☆51Updated last year
- Implementation of Concept-level Debugging of Part-Prototype Networks☆11Updated last year
- This repo implements the CVPR23 paper Trainable Projected Gradient Method for Robust Fine-tuning☆21Updated 9 months ago
- Official code of "Discover and Mitigate Unknown Biases with Debiasing Alternate Networks" (ECCV 2022)☆23Updated last year
- SpuCo is a Python package developed to further research to address spurious correlations.☆20Updated 3 months ago
- Test-Time Adaptation via Conjugate Pseudo-Labels☆36Updated last year
- Official Code Release for "Diagnosing and Rectifying Vision Models using Language" (ICLR 2023)☆31Updated last year
- The example of correspondence between fine classes and superclass (coarse class) in ImageNet.☆11Updated 2 years ago
- ImageNetV2 Pytorch Dataset☆36Updated last year
- ☆34Updated 4 months ago
- Code for Continuously Changing Corruptions (CCC) benchmark + evaluation☆28Updated 3 weeks ago
- LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images☆27Updated 9 months ago
- The repository for the official Biased Action Recognition (BAR) dataset for the paper Learning from Failure: Training Debiased Classifier…☆30Updated 3 years ago
- Create generated datasets and train robust classifiers☆35Updated last year
- Implementation of the paper "A Framework for Learning Ante-hoc Explainable Models via Concepts" (CVPR 2022).☆8Updated 2 months ago
- Official implementation of BPA (CVPR 2022)☆12Updated 2 years ago
- What do we learn from inverting CLIP models?☆41Updated 6 months ago
- Official PyTorch implementation of "CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning" @ ICCV 2023☆27Updated 8 months ago
- ☆20Updated 3 months ago
- ☆45Updated 10 months ago
- Natural Language Descriptions of Deep Visual Features, ICLR 2022☆61Updated last year
- Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning☆113Updated last year
- ☆25Updated 6 months ago
- Official code of "Discover and Cure: Concept-aware Mitigation of Spurious Correlation" (ICML 2023)☆39Updated 5 months ago
- Learning Bottleneck Concepts in Image Classification (CVPR 2023)☆33Updated 10 months ago