Structured learning of metric ensembles with application to person re-identification

TL;DR

This paper introduces structured learning methods for adaptive metric ensemble in person re-identification, improving recognition across diverse datasets by directly optimizing CMC evaluation metrics.

Contribution

It proposes two novel optimization algorithms, CMCtriplet and CMCstruct, for adaptive metric ensemble learning tailored to person re-identification.

Findings

Enhanced recognition accuracy across multiple datasets

Direct optimization of CMC evaluation metrics

Effective combination of multiple visual features

Abstract

Matching individuals across non-overlapping camera networks, known as person re-identification, is a fundamentally challenging problem due to the large visual appearance changes caused by variations of viewpoints, lighting, and occlusion. Approaches in literature can be categoried into two streams: The first stream is to develop reliable features against realistic conditions by combining several visual features in a pre-defined way; the second stream is to learn a metric from training data to ensure strong inter-class differences and intra-class similarities. However, seeking an optimal combination of visual features which is generic yet adaptive to different benchmarks is a unsoved problem, and metric learning models easily get over-fitted due to the scarcity of training data in person re-identification. In this paper, we propose two effective structured learning based approaches which explore the adaptive effects of visual features in recognizing persons in different benchmark data sets. Our framework is built on the basis of multiple low-level visual features with an optimal ensemble of their metrics. We formulate two optimization algorithms, CMCtriplet and CMCstruct, which directly optimize evaluation measures commonly used in person re-identification, also known as the Cumulative Matching Characteristic (CMC) curve.