PD-Loss: Proxy-Decidability for Efficient Metric Learning

TL;DR

PD-Loss introduces a scalable, distribution-aware metric learning method that combines proxy-based efficiency with global distribution optimization, improving embedding quality in tasks like face verification.

Contribution

It proposes a novel proxy-based loss leveraging decidability index, enabling efficient and effective distribution-aware deep metric learning.

Findings

Achieves competitive performance on face verification tasks.

Offers scalable training comparable to existing proxy methods.

Provides a new perspective on embedding optimization using distribution statistics.

Abstract

Deep Metric Learning (DML) aims to learn embedding functions that map semantically similar inputs to proximate points in a metric space while separating dissimilar ones. Existing methods, such as pairwise losses, are hindered by complex sampling requirements and slow convergence. In contrast, proxy-based losses, despite their improved scalability, often fail to optimize global distribution properties. The Decidability-based Loss (D-Loss) addresses this by targeting the decidability index (d') to enhance distribution separability, but its reliance on large mini-batches imposes significant computational constraints. We introduce Proxy-Decidability Loss (PD-Loss), a novel objective that integrates learnable proxies with the statistical framework of d' to optimize embedding spaces efficiently. By estimating genuine and impostor distributions through proxies, PD-Loss combines the computational efficiency of proxy-based methods with the principled separability of D-Loss, offering a scalable approach to distribution-aware DML. Experiments across various tasks, including fine-grained classification and face verification, demonstrate that PD-Loss achieves performance comparable to that of state-of-the-art methods while introducing a new perspective on embedding optimization, with potential for broader applications.