Identifying Interpretable Subspaces in Image Representations
Jul 24, 2023
Sprecher:innen
Über
We propose Automatic Feature Explanation using Contrasting Concepts (FALCON), an interpretability framework to explain features of image representations. For a target feature, FALCON captions its highly activating cropped images using a large captioning dataset (like LAION-400m) and a pre-trained vision-language model like CLIP. Each word among the captions is scored and ranked leading to a small number of shared, human-understandable concepts that closely describe the target feature. FALCON also applies contrastive interpretation using lowly activating (counterfactual) images, to eliminate spurious concepts. Although many existing approaches interpret features independently, we observe in state-of-the-art self-supervised and supervised models, that less than 20We propose Automatic Feature Explanation using Contrasting Concepts (FALCON), an interpretability framework to explain features of image representations. For a target feature, FALCON captions its highly activating cropped images using a large captioning dataset (like LAION-400m) and a pre-trained vision-language model like CLIP. Each word among the captions is scored and ranked leading to a small number of shared, human-understandable concepts that closely describe the target feature. FALCON als…
Gefällt euch das Format? Vertraut auf SlidesLive, um euer nächstes Event festzuhalten!
Professionelle Aufzeichnung und Livestreaming – weltweit.
Freigeben
Empfohlene Videos
Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind
Opening remarks: Duality Principles for Modern Machine Learning
Später ansehen
Zelda Mariet, …
A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks
Später ansehen
Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score
Später ansehen
Shuhai Zhang, …
Toward Fast Grad-Based Value Estimation
Später ansehen
Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards
Später ansehen
Yulian Wu, …
Fourmer: An Efficient Global Modeling Paradigm for Image Restoration
Später ansehen
Man Zhou, …