paper-with-me

Papers

Feature Visualization

2020-01-10 · Distill 2020 1 · Chris Olah, Alexander Mordvintsev, Ludwig Schubert

There is a growing sense that neural networks need to be interpretable to humans. The field of neural network interpretability has formed in response to these concerns. As it matures, two major threads of research have begun to coalesce: feature visualization and attribution. This article focuses on feature visualization. While feature visualization is a powerful tool, actually getting it to work involves a number of details. In this article, we examine the major issues and explore common approaches to solving them. We find that remarkably simple methods can produce high-quality visualizations. Along the way we introduce a few tricks for exploring variation in what neurons react to, how they interact, and how to improve the optimization process.

📄 PDF Abstract BibTeX

Code (1)

tensorflow/lucid tf

Similar Papers 제목 키워드 기반

Don't trust your eyes: on the (un)reliability of feature visualizations

2023-06-07 · Robert Geirhos, Roland S. Zimmermann, Blair Bilodeau, Wieland Brendel 외

How do neural networks extract patterns from pixels? Feature visualizations attempt to answer this important question by visualizing highly activating patterns through optimization. Today, visualization methods form the …

Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization

2023-06-11 · Thomas Fel, Thibaut Boissin, Victor Boutin, Agustin Picard 외

Feature visualization has gained substantial popularity, particularly after the influential work by Olah et al. in 2017, which established it as a crucial tool for explainability. However, its widespread adoption has bee…

Inverting the Feature Visualization Process for Feedforward Neural Networks

2020-07-21 · Christian Reinbold, Rüdiger Westermann

This work sheds light on the invertibility of feature visualization in neural networks. Since the input that is generated by feature visualization using activation maximization does, in general, not yield the feature obj…

Exemplary natural images explain CNN activations better than synthetic feature visualizations

2021-01-01 · ICLR 2021 1 · Judy Borowski, Roland Simon Zimmermann, Judith Schepers, Robert Geirhos 외

Feature visualizations such as synthetic maximally activating images are a widely used explanation method to better understand the information processing of convolutional neural networks (CNNs). At the same time, there a…

Informativeness

Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization

2023-09-21 · NeurIPS 2023 11

Feature visualization has gained significant popularity as an explainability method, particularly after the influential work by Olah et al. in 2017. Despite its success, its widespread adoption has been limited due to is…