A New Similarity Space Tailored for Supervised Deep Metric Learning
This work addresses the challenge of representing complex similarity structures in metric learning, offering a domain-specific improvement for tasks like image retrieval or classification.
The authors tackled the problem of supervised deep metric learning by proposing a novel latent space (S-space) with markers to identify similarity regions, achieving superior performance over nine existing methods across 28 datasets according to four quantitative metrics.
We propose a novel deep metric learning method. Differently from many works on this area, we defined a novel latent space obtained through an autoencoder. The new space, namely S-space, is divided into different regions that describe the positions where pairs of objects are similar/dissimilar. We locate makers to identify these regions. We estimate the similarities between objects through a kernel-based t-student distribution to measure the markers' distance and the new data representation. In our approach, we simultaneously estimate the markers' position in the S-space and represent the objects in the same space. Moreover, we propose a new regularization function to avoid similar markers to collapse altogether. We present evidences that our proposal can represent complex spaces, for instance, when groups of similar objects are located in disjoint regions. We compare our proposal to 9 different distance metric learning approaches (four of them are based on deep-learning) on 28 real-world heterogeneous datasets. According to the four quantitative metrics used, our method overcomes all the nine strategies from the literature.