Existing deep convolutional neural network (CNN) architectures are trained as N-way classifiers to distinguish between N output classes. This work builds on the intuition that not all classes are equally difficult to distinguish from a true class label. Towards this end, we introduce hierarchical branching CNNs, named as Hierarchical Deep CNN (HD-CNN), wherein classes that can be easily distinguished are classified in the higher layer coarse category CNN, while the most difficult classifications are done on lower layer fine category CNN. We propose utilizing a multinomial logistic loss and a novel temporal sparsity penalty for HD-CNN training. Together they ensure each branching component deals with a subset of categories confusing to each other. This new network architecture adopts coarse-to-fine classification strategy and module design principle. The proposed model achieves superior performance over standard models. We demonstrate state-of-the-art results on CIFAR100 benchmark.

本文提出了一种基于分层结构的深度卷积神经网络(HD-CNNs)，易分类的类别使用粗分类器进行区分，难分类的类别使用细分类器进行区分，并使用条件执行和层参数压缩等技术提高了可扩展性，成功地在CIFAR100和ImageNet等基准数据集上取得了最优结果。

HD-CNN：用于大规模视觉识别的分层深度卷积神经网络