Deep Attributes Driven Multi-Camera Person Re-identification

TL;DR

This paper introduces a semi-supervised deep attribute learning framework for multi-camera person re-identification, leveraging robust mid-level attributes to improve accuracy across diverse datasets.

Contribution

It proposes a novel three-stage training process that enhances attribute robustness and generalization for person ReID using limited labeled data.

Findings

Deep attributes outperform traditional features in ReID accuracy.

The method achieves state-of-the-art results on four datasets.

A simple metric learning module further improves performance.

Abstract

The visual appearance of a person is easily affected by many factors like pose variations, viewpoint changes and camera parameter differences. This makes person Re-Identification (ReID) among multiple cameras a very challenging task. This work is motivated to learn mid-level human attributes which are robust to such visual appearance variations. And we propose a semi-supervised attribute learning framework which progressively boosts the accuracy of attributes only using a limited number of labeled data. Specifically, this framework involves a three-stage training. A deep Convolutional Neural Network (dCNN) is first trained on an independent dataset labeled with attributes. Then it is fine-tuned on another dataset only labeled with person IDs using our defined triplet loss. Finally, the updated dCNN predicts attribute labels for the target dataset, which is combined with the independent dataset for the final round of fine-tuning. The predicted attributes, namely \emph{deep attributes} exhibit superior generalization ability across different datasets. By directly using the deep attributes with simple Cosine distance, we have obtained surprisingly good accuracy on four person ReID datasets. Experiments also show that a simple metric learning modular further boosts our method, making it significantly outperform many recent works.