Potential Field Based Deep Metric Learning

TL;DR

This paper introduces a novel deep metric learning approach using continuous potential fields to model interactions among embeddings, improving performance on standard benchmarks by handling intra-class variations and label noise.

Contribution

The paper proposes a compositional DML model that uses potential fields instead of tuples, with decay of influence over distance, enhancing robustness and accuracy.

Findings

Outperforms state-of-the-art on Cars-196, CUB-200-2011, and SOP datasets.

Effective in handling large intra-class variations.

Reduces influence of distant samples, improving learning stability.

Abstract

Deep metric learning (DML) involves training a network to learn a semantically meaningful representation space. Many current approaches mine n-tuples of examples and model interactions within each tuplets. We present a novel, compositional DML model that instead of in tuples, represents the influence of each example (embedding) by a continuous potential field, and superposes the fields to obtain their combined global potential field. We use attractive/repulsive potential fields to represent interactions among embeddings from images of the same/different classes. Contrary to typical learning methods, where mutual influence of samples is proportional to their distance, we enforce reduction in such influence with distance, leading to a decaying field. We show that such decay helps improve performance on real world datasets with large intra-class variations and label noise. Like other proxy-based methods, we also use proxies to succinctly represent sub-populations of examples. We evaluate our method on three standard DML benchmarks- Cars-196, CUB-200-2011, and SOP datasets where it outperforms state-of-the-art baselines.