Single Camera Training for Person Re-identification

TL;DR

This paper introduces a novel single-camera training setting for person re-identification, proposing a new loss function that enhances accuracy without requiring cross-camera annotations, thus simplifying deployment in new environments.

Contribution

It pioneers the single-camera training (SCT) setting for ReID and proposes the multi-camera negative loss (MCNL) to improve discriminative feature learning without cross-camera data.

Findings

MCNL significantly improves ReID accuracy in SCT setting

SCT reduces data collection and annotation costs

Proposed method enables faster deployment in new environments

Abstract

Person re-identification (ReID) aims at finding the same person in different cameras. Training such systems usually requires a large amount of cross-camera pedestrians to be annotated from surveillance videos, which is labor-consuming especially when the number of cameras is large. Differently, this paper investigates ReID in an unexplored single-camera-training (SCT) setting, where each person in the training set appears in only one camera. To the best of our knowledge, this setting was never studied before. SCT enjoys the advantage of low-cost data collection and annotation, and thus eases ReID systems to be trained in a brand new environment. However, it raises major challenges due to the lack of cross-camera person occurrences, which conventional approaches heavily rely on to extract discriminative features. The key to dealing with the challenges in the SCT setting lies in designing an effective mechanism to complement cross-camera annotation. We start with a regular deep network for feature extraction, upon which we propose a novel loss function named multi-camera negative loss (MCNL). This is a metric learning loss motivated by probability, suggesting that in a multi-camera system, one image is more likely to be closer to the most similar negative sample in other cameras than to the most similar negative sample in the same camera. In experiments, MCNL significantly boosts ReID accuracy in the SCT setting, which paves the way of fast deployment of ReID systems with good performance on new target scenes.