Temporal Continuity Based Unsupervised Learning for Person Re-Identification

TL;DR

This paper introduces TCUL, an unsupervised learning framework that leverages temporal continuity and clustering to improve person re-identification without labeled data, demonstrating superior performance on large benchmarks.

Contribution

The paper proposes a novel unsupervised, center-based clustering approach that exploits temporal and spatial cues for person re-id, reducing reliance on labeled datasets.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Effectively learns discriminative features without labeled data

Progressively improves with more reliable pseudo-labels

Abstract

Person re-identification (re-id) aims to match the same person from images taken across multiple cameras. Most existing person re-id methods generally require a large amount of identity labeled data to act as discriminative guideline for representation learning. Difficulty in manually collecting identity labeled data leads to poor adaptability in practical scenarios. To overcome this problem, we propose an unsupervised center-based clustering approach capable of progressively learning and exploiting the underlying re-id discriminative information from temporal continuity within a camera. We call our framework Temporal Continuity based Unsupervised Learning (TCUL). Specifically, TCUL simultaneously does center based clustering of unlabeled (target) dataset and fine-tunes a convolutional neural network (CNN) pre-trained on irrelevant labeled (source) dataset to enhance discriminative capability of the CNN for the target dataset. Furthermore, it exploits temporally continuous nature of images within-camera jointly with spatial similarity of feature maps across-cameras to generate reliable pseudo-labels for training a re-identification model. As the training progresses, number of reliable samples keep on growing adaptively which in turn boosts representation ability of the CNN. Extensive experiments on three large-scale person re-id benchmark datasets are conducted to compare our framework with state-of-the-art techniques, which demonstrate superiority of TCUL over existing methods.