GitHub / Trustworthy-ML-Lab / posthoc-generative-cbm
[CVPR 2025] Concept Bottleneck Autoencoder (CB-AE) -- efficiently transform any pretrained (black-box) image generative model into an interpretable generative concept bottleneck model (CBM) with minimal concept supervision, while preserving image quality
Stars: 5
Forks: 0
Open issues: 0
License: None
Language: Jupyter Notebook
Size: 3 MB
Dependencies parsed at: Pending
Created at: 2 months ago
Updated at: 2 days ago
Pushed at: 3 days ago
Last synced at: 2 days ago
Topics: computer-vision, concept-bottleneck-models, deep-learning, generative-ai, interpretability-and-explainability, interpretable-deep-learning, mechanistic-interpretability