Image retrieval based on learning to rank and multiple loss

Abstract

Image retrieval applying deep convolutional features has achieved the most advanced performance in most standard benchmark tests. In image retrieval, deep metric learning (DML) plays a key role and aims to capture semantic similarity information carried by data points. However, two factors may impede the accuracy of image retrieval. First, when learning the similarity of negative examples, current methods separate negative pairs into equal distance in the embedding space. Thus, the intraclass data distribution might be missed. Second, given a query, either a fraction of data points, or all of them, are incorporated to build up the similarity structure, which makes it rather complex to calculate similarity or to choose example pairs. In this study, in order to achieve more accurate image retrieval, we proposed a method based on learning to rank and multiple loss (LRML). To address the first problem, through learning the ranking sequence, we separate the negative pairs from the query image into different distance. To tackle the second problem, we used a positive example in the gallery and negative sets from the bottom five ranked by similarity, thereby enhancing training efficiency. Our significant experimental results demonstrate that the proposed method achieves state-of-the-art performance on three widely used benchmarks.