Can computer vision problems benefit from structured hierarchical classification?

Hoyoux, Thomas; Rodríguez-Sánchez, Antonio Jose; Piater, Justus

doi:10.1007/s00138-016-0763-9

Cited by 9 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Song et al [8] study dataless hierarchical text classification with unsupervised methods. Hoyoux et al [15] show some counter-examples where using hierarchical methods degrades the accuracy, and explore the reasons for such results. Oh [9] studies the combination of hierarchical classification and top-k accuracy.…”

Section: Related Workmentioning

confidence: 99%

Understanding the Impact of Label Granularity on CNN-Based Image Classification

Chen

Ding

Chin

et al. 2018

2018 IEEE International Conference on Data Mining Workshops (ICDMW)

View full text Add to dashboard Cite

In recent years, supervised learning using Convolutional Neural Networks (CNNs) has achieved great success in image classification tasks, and large scale labeled datasets have contributed significantly to this achievement. However, the definition of a label is often application dependent. For example, an image of a cat can be labeled as "cat" or perhaps more specifically "Persian cat." We refer to this as label granularity. In this paper, we conduct extensive experiments using various datasets to demonstrate and analyze how and why training based on fine-grain labeling, such as "Persian cat" can improve CNN accuracy on classifying coarse-grain classes, in this case "cat."The experimental results show that training CNNs with finegrain labels improves both network's optimization and generalization capabilities, as intuitively it encourages the network to learn more features, and hence increases classification accuracy on coarse-grain classes under all datasets considered. Moreover, fine-grain labels enhance data efficiency in CNN training. For example, a CNN trained with fine-grain labels and only 40% of the total training data can achieve higher accuracy than a CNN trained with the full training dataset and coarse-grain labels. These results point to two possible applications of this work: (i) with sufficient human resources, one can improve CNN performance by re-labeling the dataset with fine-grain labels, and (ii) with limited human resources, to improve CNN performance, rather than collecting more training data, one may instead use fine-grain labels for the dataset. We also observe that the improvement brought by fine-grain labeling varies from dataset to dataset, therefore we further propose a metric called Average Confusion Ratio to characterize the effectiveness of fine-grain labeling, and show its use through extensive experimentation. Code is available at https://github.com/cmu-enyac/Label-Granularity.

show abstract

Section: Related Workmentioning

confidence: 99%