Deeply Coupled Auto-encoder Networks for Cross-view Classification
This addresses cross-view classification for image analysis, but appears incremental as it builds on existing auto-encoder and coupling techniques.
The paper tackles cross-view image classification by proposing Deeply Coupled Autoencoder Networks (DCAN), which uses coupled neural networks to narrow the gap between views, achieving superior performance over state-of-the-art methods in experiments.
The comparison of heterogeneous samples extensively exists in many applications, especially in the task of image classification. In this paper, we propose a simple but effective coupled neural network, called Deeply Coupled Autoencoder Networks (DCAN), which seeks to build two deep neural networks, coupled with each other in every corresponding layers. In DCAN, each deep structure is developed via stacking multiple discriminative coupled auto-encoders, a denoising auto-encoder trained with maximum margin criterion consisting of intra-class compactness and inter-class penalty. This single layer component makes our model simultaneously preserve the local consistency and enhance its discriminative capability. With increasing number of layers, the coupled networks can gradually narrow the gap between the two views. Extensive experiments on cross-view image classification tasks demonstrate the superiority of our method over state-of-the-art methods.