Combining human parsing with analytical feature extraction and ranking schemes for high-generalization person reidentification

TL;DR

This paper introduces a high-generalization person re-identification method combining analytical feature extraction, ranking schemes, and human parsing, achieving superior cross-domain accuracy without training, and enabling human-like query searches.

Contribution

The paper presents a trainable-parameter-free model that integrates analytical features with deep learning human parsing for improved generalization in person re-ID.

Findings

Achieves 63.9% and 93.5% rank-1 cross-domain accuracy.

Performs comparably to deep learning models on benchmark datasets.

Enables human-generated verbal queries for person search.

Abstract

Person reidentification (re-ID) has been receiving increasing attention in recent years due to its importance for both science and society. Machine learning and particularly Deep Learning (DL) has become the main re-id tool that allowed researches to achieve unprecedented accuracy levels on benchmark datasets. However, there is a known problem of poor generalization of DL models. That is, models trained to achieve high accuracy on one dataset perform poorly on other ones and require re-training. To address this issue, we present a model without trainable parameters which shows great potential for high generalization. It combines a fully analytical feature extraction and similarity ranking scheme with DL-based human parsing used to obtain the initial subregion classification. We show that such combination to a high extent eliminates the drawbacks of existing analytical methods. We use interpretable color and texture features which have human-readable similarity measures associated with them. To verify the proposed method we conduct experiments on Market1501 and CUHK03 datasets achieving competitive rank-1 accuracy comparable with that of DL-models. Most importantly we show that our method achieves 63.9% and 93.5% rank-1 cross-domain accuracy when applied to transfer learning tasks. It is significantly higher than previously reported 30-50% transfer accuracy. We discuss the potential ways of adding new features to further improve the model. We also show the advantage of interpretable features for constructing human-generated queries from verbal description to conduct search without a query image.