Analyzing Learned Convnet Features with Dirichlet Process Gaussian Mixture Models
This work addresses the problem of interpretability in deep learning for computer vision researchers, but it is incremental as it applies an existing clustering method to a known bottleneck.
The paper tackles the challenge of visualizing high-dimensional internal representations in Convolutional Neural Networks (Convnets) by clustering these representations using a Dirichlet Process Gaussian Mixture Model, which helps interpret learned features and is useful for transfer learning.
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.