Reconstruction Regularized Deep Metric Learning for Multi-label Image Classification
This addresses the problem of accurately classifying images with multiple labels for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles multi-label image classification by proposing a deep metric learning method that embeds images and labels into a latent space with a two-way distance metric and a reconstruction regularization term, achieving improved performance over state-of-the-art methods on public datasets.
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.