A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networks
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
ETE 3: Reconstruction, Analysis, and Visualization of Phylogenomic Data
The Environment for Tree Exploration (ETE) is a computational framework that simplifies the reconstruction, analysis, and visualization of phylogenetic trees and multiple sequence alignments. Here, we present ETE v3, fea…
A Configurable Library for Generating and Manipulating Maze Datasets
Understanding how machine learning models respond to distributional shifts is a key research challenge. Mazes serve as an excellent testbed due to varied generation algorithms offering a nuanced platform to simulate both…
Analyzing Learned Convnet Features with Dirichlet Process Gaussian Mixture Models
Convolutional Neural Networks (Convnets) have achieved good results in a range of computer vision tasks the recent years. Though given a lot of attention, visualizing the learned representations to interpret Convnets, st…
ClusteringTransfer LearningSODA: a TypeScript/JavaScript Library for Visualizing Biological Sequence Annotation
We present SODA, a lightweight and open-source visualization library for biological sequence annotations that enables straightforward development of flexible, dynamic, and interactive web graphics. SODA is implemented in…
A functionality taxonomy for document search engines
In this paper a functionality taxonomy for document search engines is proposed. It can be used to assess the features of a search engine, to position search engines relative to each other, or to select which search engin…