# A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1606.07757 · HTML: https://mlsanity.com/paper/1606.07757/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2016.

## Built on by (most cited first, 7 of 7)

- [The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations](https://mlsanity.com/paper/2212.11737/) (2022)
- [Towards Human-Understandable Visual Explanations:Imperceptible High-frequency Cues Can Better Be Removed](https://mlsanity.com/paper/2104.07954/) (2021)
- [Geo-Context Aware Study of Vision-Based Autonomous Driving Models and Spatial Video Data](https://mlsanity.com/paper/2109.10895/) (2021)
- [Localisation of Mammographic masses by Greedy Backtracking of Activations in the Stacked Auto-Encoders](https://mlsanity.com/paper/2305.05136/) (2023)
- [Towards the Characterization of Representations Learned via Capsule-based Network Architectures](https://mlsanity.com/paper/2305.05349/) (2023)
- [FICNN: A Framework for the Interpretation of Deep Convolutional Neural Networks](https://mlsanity.com/paper/2305.10121/) (2023)
- [Towards Predicting the Success of Transfer-based Attacks by Quantifying Shared Feature Representations](https://mlsanity.com/paper/2412.05351/) (2024)

## Abstract (arXiv)

Over the last decade, Convolutional Neural Networks (CNN) saw a tremendous surge in performance. However, understanding what a network has learned still proves to be a challenging task. To remedy this unsatisfactory situation, a number of groups have recently proposed different methods to visualize the learned models. In this work we suggest a general taxonomy to classify and compare these methods, subdividing the literature into three main categories and providing researchers with a terminology to base their works on. Furthermore, we introduce the FeatureVis library for MatConvNet: an extendable, easy to use open source library for visualizing CNNs. It contains implementations from each of the three main classes of visualization methods and serves as a useful tool for an enhanced understanding of the features learned by intermediate layers, as well as for the analysis of why a network might fail for certain examples.