LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning

TL;DR

LoOp introduces a novel method for selecting optimal hard negatives in embedding space, improving deep metric learning by considering entire embedding pairs rather than mining strategies, leading to better performance.

Contribution

The paper proposes LoOp, a new approach that finds optimal hard negatives in embedding space, addressing biases and inefficiencies of existing hard mining and synthetic generation methods.

Findings

Significant performance improvements on three benchmark datasets.

Effective integration with various metric learning losses.

Addresses challenges of bias, optimization difficulty, and training speed.

Abstract

Deep metric learning has been effectively used to learn distance metrics for different visual tasks like image retrieval, clustering, etc. In order to aid the training process, existing methods either use a hard mining strategy to extract the most informative samples or seek to generate hard synthetics using an additional network. Such approaches face different challenges and can lead to biased embeddings in the former case, and (i) harder optimization (ii) slower training speed (iii) higher model complexity in the latter case. In order to overcome these challenges, we propose a novel approach that looks for optimal hard negatives (LoOp) in the embedding space, taking full advantage of each tuple by calculating the minimum distance between a pair of positives and a pair of negatives. Unlike mining-based methods, our approach considers the entire space between pairs of embeddings to calculate the optimal hard negatives. Extensive experiments combining our approach and representative metric learning losses reveal a significant boost in performance on three benchmark datasets.