Analyzing Learned Convnet Features with Dirichlet Process Gaussian Mixture Models

TL;DR

This paper introduces a clustering-based visualization technique for understanding high-dimensional learned features in convolutional neural networks using Dirichlet Process Gaussian Mixture Models, aiding interpretability and transfer learning.

Contribution

The paper proposes a novel clustering method for visualizing Convnet features that handles high dimensionality and enhances understanding of learned representations.

Findings

Effective clustering of internal Convnet features across layers

Improved interpretability of learned representations

Insights into transfer learning applications

Abstract

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, still remains a challenging task. The high dimensionality of internal representations and the high abstractions of deep layers are the main challenges when visualizing Convnet functionality. We present in this paper a technique based on clustering internal Convnet representations with a Dirichlet Process Gaussian Mixture Model, for visualization of learned representations in Convnets. Our method copes with the high dimensionality of a Convnet by clustering representations across all nodes of each layer. We will discuss how this application is useful when considering transfer learning, i.e.\ transferring a model trained on one dataset to solve a task on a different one.

Full text

See pages 1-last of main.pdf