Deeply Coupled Auto-encoder Networks for Cross-view Classification

TL;DR

This paper introduces Deeply Coupled Auto-encoder Networks (DCAN), a deep neural architecture designed to improve cross-view image classification by coupling auto-encoders at each layer to reduce view discrepancies.

Contribution

The paper proposes a novel deep coupled auto-encoder framework that enhances discriminative ability and view alignment in cross-view classification tasks.

Findings

DCAN outperforms state-of-the-art methods in cross-view image classification.

The layered coupling progressively narrows the gap between different views.

The model effectively preserves local consistency and discriminative features.

Abstract

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.