Fine-Grained Classification via Mixture of Deep Convolutional Neural Networks
This addresses the problem of fine-grained classification for computer vision applications, offering an incremental improvement over existing methods.
The paper tackles fine-grained image classification by proposing a mixture of deep convolutional neural networks (MixDCNN) that partitions images into subsets and trains expert networks for each, resulting in a relative improvement of 12.7% and state-of-the-art performance on two datasets.
We present a novel deep convolutional neural network (DCNN) system for fine-grained image classification, called a mixture of DCNNs (MixDCNN). The fine-grained image classification problem is characterised by large intra-class variations and small inter-class variations. To overcome these problems our proposed MixDCNN system partitions images into K subsets of similar images and learns an expert DCNN for each subset. The output from each of the K DCNNs is combined to form a single classification decision. In contrast to previous techniques, we provide a formulation to perform joint end-to-end training of the K DCNNs simultaneously. Extensive experiments, on three datasets using two network structures (AlexNet and GoogLeNet), show that the proposed MixDCNN system consistently outperforms other methods. It provides a relative improvement of 12.7% and achieves state-of-the-art results on two datasets.