Prototype Generation: Robust Feature Visualisation for Data Independent Interpretability

NeurIPS 2023 Workshop ATTRIB Submission10 Authors

Published: 27 Oct 2023, Last Modified: 08 Dec 2023ATTRIB PosterEveryoneRevisionsBibTeX
Keywords: Interpretability; Concept-based interpretability
Abstract: We introduce Prototype Generation, a stricter and more robust form of feature visualisation for model-agnostic, data-independent interpretability of image classification models. We demonstrate its ability to generate inputs that result in natural activation paths, countering previous claims that feature visualisation algorithms are untrustworthy due to the unnatural internal activations. We substantiate these claims by quantitatively measuring similarity between the internal activations of our generated prototypes and natural images. We also demonstrate how the interpretation of generated prototypes yields important insights, highlighting spurious correlations and biases learned by models which quantitative methods over test-sets cannot identify.
Submission Number: 10