Deep metric learning: A survey

M Kaya, HŞ Bilge - Symmetry, 2019 - mdpi.com
Metric learning aims to measure the similarity among samples while using an optimal
distance metric for learning tasks. Metric learning methods, which generally use a linear …

Random erasing data augmentation

Z Zhong, L Zheng, G Kang, S Li, Y Yang - Proceedings of the AAAI …, 2020 - ojs.aaai.org
In this paper, we introduce Random Erasing, a new data augmentation method for training
the convolutional neural network (CNN). In training, Random Erasing randomly selects a …

In defense of the triplet loss for person re-identification

A Hermans, L Beyer, B Leibe - arxiv preprint arxiv:1703.07737, 2017 - arxiv.org
In the past few years, the field of computer vision has gone through a revolution fueled
mainly by the advent of large datasets and the adoption of deep convolutional neural …

Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline)

Y Sun, L Zheng, Y Yang, Q Tian… - Proceedings of the …, 2018 - openaccess.thecvf.com
Employing part-level features offers fine-grained information for pedestrian image
description. A prerequisite of part discovery is that each part should be well located. Instead …

Unlabeled samples generated by gan improve the person re-identification baseline in vitro

Z Zheng, L Zheng, Y Yang - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
The main contribution of this paper is a simple semi-supervised pipeline that only uses the
original training set without collecting extra data. It is challenging in 1) how to obtain more …

Towards real-time multi-object tracking

Z Wang, L Zheng, Y Liu, Y Li, S Wang - European conference on computer …, 2020 - Springer
Modern multiple object tracking (MOT) systems usually follow the tracking-by-detection
paradigm. It has 1) a detection model for target localization and 2) an appearance …

Part-based pseudo label refinement for unsupervised person re-identification

Y Cho, WJ Kim, S Hong… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Unsupervised person re-identification (re-ID) aims at learning discriminative representations
for person retrieval from unlabeled data. Recent techniques accomplish this task by using …

Learning discriminative features with multiple granularities for person re-identification

G Wang, Y Yuan, X Chen, J Li, X Zhou - Proceedings of the 26th ACM …, 2018 - dl.acm.org
The combination of global and partial features has been an essential solution to improve
discriminative performances in person re-identification (Re-ID) tasks. Previous part-based …

Diverse part discovery: Occluded person re-identification with part-aware transformer

Y Li, J He, T Zhang, X Liu… - Proceedings of the …, 2021 - openaccess.thecvf.com
Occluded person re-identification (Re-ID) is a challenging task as persons are frequently
occluded by various obstacles or other persons, especially in the crowd scenario. To …