Denoising Multi-Similarity Formulation: A Self-paced Curriculum-Driven Approach for Robust Metric Learning

TL;DR

This paper introduces BSPML, a robust deep metric learning method that effectively handles noisy data by integrating self-paced learning with a denoising multi-similarity formulation, improving generalization and robustness.

Contribution

The paper proposes a novel BSPML algorithm that models noisy samples as hard samples and adaptively excludes them, with a new regularization term and an efficient optimization algorithm.

Findings

BSPML outperforms existing methods in robustness and generalization.

The proposed algorithm converges theoretically.

Experimental results validate the effectiveness of BSPML.

Abstract

Deep Metric Learning (DML) is a group of techniques that aim to measure the similarity between objects through the neural network. Although the number of DML methods has rapidly increased in recent years, most previous studies cannot effectively handle noisy data, which commonly exists in practical applications and often leads to serious performance deterioration. To overcome this limitation, in this paper, we build a connection between noisy samples and hard samples in the framework of self-paced learning, and propose a \underline{B}alanced \underline{S}elf-\underline{P}aced \underline{M}etric \underline{L}earning (BSPML) algorithm with a denoising multi-similarity formulation, where noisy samples are treated as extremely hard samples and adaptively excluded from the model training by sample weighting. Especially, due to the pairwise relationship and a new balance regularization term, the sub-problem \emph{w.r.t.} sample weights is a nonconvex quadratic function. To efficiently solve this nonconvex quadratic problem, we propose a doubly stochastic projection coordinate gradient algorithm. Importantly, we theoretically prove the convergence not only for the doubly stochastic projection coordinate gradient algorithm, but also for our BSPML algorithm. Experimental results on several standard data sets demonstrate that our BSPML algorithm has better generalization ability and robustness than the state-of-the-art robust DML approaches.