A New Similarity Space Tailored For Supervised Deep Metric Learning

Abstract

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-wor

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keybarros2020a

Related papers

• Metric Learning By Similarity Network For Deep Semi-supervised Learning (2020)3.58
• S2SD: Simultaneous Similarity-based Self-distillation For Deep Metric Learning (2020)3.31
• Deep Metric Learning Assisted By Intra-variance In A Semi-supervised View Of Learning (2023)5.24
• Signal-to-noise Ratio: A Robust Distance Metric For Deep Metric Learning (2019)13.60
• Deep Metric Learning Using Similarities From Nonlinear Rank Approximations (2019)2.26
• Divide And Conquer The Embedding Space For Metric Learning (2019)14.39
• Deep Metric Learning-based Semi-supervised Regression With Alternate Learning (2022)5.24
• Deep Metric Learning Beyond Binary Supervision (2019)14.39