Going Deeper into Semi-supervised Person Re-identification

TL;DR

This paper introduces a semi-supervised person re-identification method using part-based features from a single CNN and a novel PartMixUp loss, reducing labeled data needs while maintaining high accuracy.

Contribution

It proposes a practical semi-supervised approach with part-based features and PartMixUp loss, eliminating the need for known identity counts and improving efficiency.

Findings

Outperforms state-of-the-art on three datasets

Achieves full supervision performance with only one-third labeled data

Reduces computational resources needed for training

Abstract

Person re-identification is the challenging task of identifying a person across different camera views. Training a convolutional neural network (CNN) for this task requires annotating a large dataset, and hence, it involves the time-consuming manual matching of people across cameras. To reduce the need for labeled data, we focus on a semi-supervised approach that requires only a subset of the training data to be labeled. We conduct a comprehensive survey in the area of person re-identification with limited labels. Existing works in this realm are limited in the sense that they utilize features from multiple CNNs and require the number of identities in the unlabeled data to be known. To overcome these limitations, we propose to employ part-based features from a single CNN without requiring the knowledge of the label space (i.e., the number of identities). This makes our approach more suitable for practical scenarios, and it significantly reduces the need for computational resources. We also propose a PartMixUp loss that improves the discriminative ability of learned part-based features for pseudo-labeling in semi-supervised settings. Our method outperforms the state-of-the-art results on three large-scale person re-id datasets and achieves the same level of performance as fully supervised methods with only one-third of labeled identities.