Reconstruction Regularized Deep Metric Learning for Multi-label Image Classification

Abstract

In this paper, we present a novel deep metric learning method to tackle the multi-label image classification problem. In order to better learn the correlations among images features, as well as labels, we attempt to explore a latent space, where images and labels are embedded via two unique deep neural networks, respectively. To capture the relationships between image features and labels, we aim to learn a \emph{two-way} deep distance metric over the embedding space from two different views, i.e., the distance between one image and its labels is not only smaller than those distances between the image and its labels' nearest neighbors, but also smaller than the distances between the labels and other images corresponding to the labels' nearest neighbors. Moreover, a reconstruction module for recovering correct labels is incorporated into the whole framework as a regularization term, such that the label embedding space is more representative. Our model can be trained in an end-to-end manner. Experimental results on publicly available image datasets corroborate the efficacy of our method compared with the state-of-the-arts.

arXiv commentAccepted by IEEE TNNLS

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• CNN: Single-label to Multi-label
• Multi-Instance Multi-Label Learning
• Towards Good Practices for Very Deep Two-Stream ConvNets
• No Fuss Distance Metric Learning using Proxies
• Multi-label Image Recognition by Recurrently Discovering Attentional Regions
• Learning Deep Latent Spaces for Multi-Label Classification