Do Convolutional Neural Networks Learn Class Hierarchy?
Convolutional Neural Networks (CNNs) currently achieve state-of-the-art accuracy in image classification. With a growing number of classes, the accuracy usually drops as the possibilities of confusion increase. Interestingly, the class confusion patterns follow a hierarchical structure over the classes. We present visual-analytics methods to reveal and analyze this hierarchy of similar classes in relation with CNN-internal data. We found that this hierarchy not only dictates the confusion patterns between the classes, it furthermore dictates the learning behavior of CNNs. In particular, the early layers in these networks develop feature detectors that can separate high-level groups of classes quite well, even after a few training epochs. In contrast, the latter layers require substantially more epochs to develop specialized feature detectors that can separate individual classes. We demonstrate how these insights are key to significant improvement in accuracy by designing hierarchy-aware CNNs that accelerate model convergence and alleviate overfitting. We further demonstrate how our methods help in identifying various quality issues in the training data.
Code (0)
등록된 구현이 없습니다.
Tasks
image-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Learn Class Hierarchy using Convolutional Neural Networks
A large amount of research on Convolutional Neural Networks has focused on flat Classification in the multi-class domain. In the real world, many problems are naturally expressed as problems of hierarchical classificatio…
ClassificationGeneral ClassificationClass2Str: End to End Latent Hierarchy Learning
Deep neural networks for image classification typically consists of a convolutional feature extractor followed by a fully connected classifier network. The predicted and the ground truth labels are represented as one hot…
General Classificationimage-classificationImage ClassificationBayesian and Convolutional Networks for Hierarchical Morphological Classification of Galaxies
This work is focused on the morphological classification of galaxies following the Hubble sequence in which the different classes are arranged in a hierarchy. The proposed method, BCNN, is composed of two main modules. F…
Image AugmentationWhen Labels Have Structure: Improving Image Classification with Hierarchy-Aware Cross-Entropy
Standard cross-entropy is the default classification loss across virtually all of machine learning, yet it treats all misclassifications equally, ignoring the semantic distances that a class hierarchy encodes. We propose…
Image ClassificationB-CNN: Branch Convolutional Neural Network for Hierarchical Classification
Convolutional Neural Network (CNN) image classifiers are traditionally designed to have sequential convolutional layers with a single output layer. This is based on the assumption that all target classes should be treate…
ClassificationGeneral Classification