Hdcnn Hierarchical Deep Convolutional Neural Network For Large Scale Visual Recognition

# HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual Recognition

**arXiv ID:** 1410.0736
**Authors:** Zhicheng Yan, Hao Zhang, Robinson Piramuthu, Vignesh Jagadeesh, Dennis DeCoste, Wei Di, Yizhou Yu
**Published:** 2014-10-03T01:17:20Z
**Abstract:**
In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Such difficult categories demand more dedicated classifiers. However, existing deep convolutional neural networks (CNN) are trained as flat N-way classifiers, and few efforts have been made to leverage the hierarchical structure of categories. In this paper, we introduce hierarchical deep CNNs (HD-CNNs) by embedding deep CNNs into a category hierarchy. An HD-CNN separates easy classes using a coarse category classifier while distinguishing difficult classes using fine category classifiers. During HD-CNN training, component-wise pretraining is followed by global finetuning with a multinomial logistic loss regularized by a coarse category consistency term. In addition, conditional executions of fine category classifiers and layer parameter compression make HD-CNNs scalable for large-scale visual recognition. We achieve state-of-the-art results on both CIFAR100 and large-scale ImageNet 1000-class benchmark datasets. In our experiments, we build up three different HD-CNNs and they lower the top-1 error of the standard CNNs by 2.65%, 3.1% and 1.1%, respectively.

## Skill Description

This skill is generated from the arXiv paper: HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual Recognition (1410.0736).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:1410.0736](http://arxiv.org/abs/1410.0736v4)