PD-Loss: Proxy-Decidability for Efficient Metric Learning
This work addresses scalability and distribution optimization issues in deep metric learning for applications such as image classification and verification, representing an incremental improvement over existing proxy-based and decidability-based methods.
The paper tackled the problem of inefficient convergence and computational constraints in deep metric learning by introducing PD-Loss, which integrates learnable proxies with a statistical framework to optimize embedding spaces, achieving performance comparable to state-of-the-art methods in tasks like fine-grained classification and face verification.
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.