Classification is a Strong Baseline for Deep Metric Learning

TL;DR

This paper demonstrates that classification-based methods are a competitive and scalable approach for deep metric learning tasks like image retrieval and face verification, challenging the dominance of triplet-based methods.

Contribution

The study shows the effectiveness of classification-based deep metric learning across multiple datasets and explores techniques for scalability and efficiency.

Findings

Classification-based approaches perform competitively on standard retrieval datasets.

Subsampling classes can improve scalability without sacrificing accuracy.

Binarization enables efficient storage and computation.

Abstract

Deep metric learning aims to learn a function mapping image pixels to embedding feature vectors that model the similarity between images. Two major applications of metric learning are content-based image retrieval and face verification. For the retrieval tasks, the majority of current state-of-the-art (SOTA) approaches are triplet-based non-parametric training. For the face verification tasks, however, recent SOTA approaches have adopted classification-based parametric training. In this paper, we look into the effectiveness of classification based approaches on image retrieval datasets. We evaluate on several standard retrieval datasets such as CAR-196, CUB-200-2011, Stanford Online Product, and In-Shop datasets for image retrieval and clustering, and establish that our classification-based approach is competitive across different feature dimensions and base feature networks. We further provide insights into the performance effects of subsampling classes for scalable classification-based training, and the effects of binarization, enabling efficient storage and computation for practical applications.