期刊
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
卷 14, 期 5, 页码 -出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3610298
关键词
Single-shot person re-identification; Deep Convolutional Neural Network; neural architecture; triplet loss
This article explores the challenge of solving Person Re-Identification (Re-Id) through Deep Convolutional Neural Networks, particularly in the case of limited training data. Different neural architectures, trained using a Triplet Model, are evaluated on two challenging Single-Shot Re-Id datasets, PRID2011 and CUHK. The results suggest that Inception-ResNet and DenseNet are potentially useful models for Re-Id tasks.
Solving Person Re-Identification (Re-Id) through Deep Convolutional Neural Networks is a daunting challenge due to the small size and variety of the training data, especially in Single-Shot Re-Id, where only two images per person are available. The lack of training data causes the overfitting of the deep neural models, leading to degenerated performance. This article explores a wide assortment of neural architectures that have been commonly used for object classification and analyzes their suitability in a Re-Id model. These architectures have been trained through a Triplet Model and evaluated over two challenging Single-Shot Re-Id datasets, PRID2011 and CUHK. This comparative study is aimed at obtaining the best-performing architectures and some concluding guidance to optimize the features embedding for the Re-Identification task. The obtained results present Inception-ResNet and DenseNet as potentially useful models, especially when compared with other methods, specifically designed for solving Re-Id.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据