Directional Statistics-based Deep Metric Learning For Image Classification And Retrieval

Abstract

Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging results in many computer vision tasks.\(L2\)-normalization in the embedding space has been used to improve the performance of several DDML methods. However, the commonly used Euclidean distance is no longer an accurate metric for \(L2\)-normalized embedding space, i.e., a hyper-sphere. Another challenge of current DDML methods is that their loss functions are usually based on rigid data formats, such as the triplet tuple. Thus, an extra process is needed to prepare data in specific formats. In addition, their losses are obtained from a limited number of samples, which leads to a lack of the global view of the embedding space. In this paper, we replace the Euclidean distance with the cosine similarity to better utilize the \(L2\)-normalization, which is able to attenuate the curse of dimensionality. More speci

Stats

• citations54
• S2 citations—
• github stars0
• HF likes0
• heat score13.05
• arxiv keyzhe2018directional

Related papers

• Guided Deep Metric Learning (2022)6.77
• Unbiased Evaluation Of Deep Metric Learning Algorithms (2019)0.00
• Deep Relational Metric Learning (2021)12.17
• Improving Deep Metric Learning By Divide And Conquer (2021)8.09
• A Framework To Enhance Generalization Of Deep Metric Learning Methods Using General Discriminative Feature Learning And Class Adversarial Neural Networks (2021)7.50
• Signal-to-noise Ratio: A Robust Distance Metric For Deep Metric Learning (2019)13.60
• Deep Metric Learning Meets Deep Clustering: An Novel Unsupervised Approach For Feature Embedding (2020)2.26
• Deep Metric Learning Using Similarities From Nonlinear Rank Approximations (2019)2.26