Multi-level Distance Regularization for Deep Metric Learning

TL;DR

This paper introduces Multi-level Distance Regularization (MDR), a novel method for deep metric learning that improves generalization and performance by regularizing pairwise distances at multiple levels, achieving state-of-the-art results.

Contribution

The paper proposes MDR, a new regularization technique that enhances deep metric learning by disturbing the learning process at multiple distance levels, leading to better generalization and performance.

Findings

MDR with Triplet loss achieves state-of-the-art results on multiple benchmarks.

MDR improves the robustness and generalization of deep metric learning models.

Extensive ablation studies confirm the effectiveness of MDR.

Abstract

We propose a novel distance-based regularization method for deep metric learning called Multi-level Distance Regularization (MDR). MDR explicitly disturbs a learning procedure by regularizing pairwise distances between embedding vectors into multiple levels that represents a degree of similarity between a pair. In the training stage, the model is trained with both MDR and an existing loss function of deep metric learning, simultaneously; the two losses interfere with the objective of each other, and it makes the learning process difficult. Moreover, MDR prevents some examples from being ignored or overly influenced in the learning process. These allow the parameters of the embedding network to be settle on a local optima with better generalization. Without bells and whistles, MDR with simple Triplet loss achieves the-state-of-the-art performance in various benchmark datasets: CUB-200-2011, Cars-196, Stanford Online Products, and In-Shop Clothes Retrieval. We extensively perform ablation studies on its behaviors to show the effectiveness of MDR. By easily adopting our MDR, the previous approaches can be improved in performance and generalization ability.