Scalable Person Re-Identification by Harmonious Attention
Open Access
- 23 December 2019
- journal article
- research article
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 128 (6) , 1635-1653
Abstract
Existing person re-identification (re-id) deep learning methods rely heavily on the utilisation of large and computationally expensive convolutional neural networks. They are thereforenot scalableto large scale re-id deployment scenarios with the need of processing a large amount of surveillance video data, due to the lengthy inference process with high computing costs. In this work, we address this limitation via jointly learning re-id attention selection. Specifically, we formulate a novelharmonious attention network(HAN) framework to jointly learn soft pixel attention and hard region attention alongside simultaneous deep feature representation learning, particularly enabling more discriminative re-id matching byefficientnetworks with more scalable model inference and feature matching. Extensive evaluations validate the cost-effectiveness superiority of the proposed HAN approach for person re-id against a wide variety of state-of-the-art methods on four large benchmark datasets: CUHK03, Market-1501, DukeMTMC, and MSMT17.Keywords
Funding Information
- Queen Mary University of London
This publication has 84 references indexed in Scilit:
- Bit-Scalable Deep Hashing With Regularized Similarity Learning for Image Retrieval and Person Re-IdentificationIEEE Transactions on Image Processing, 2015
- Unsupervised Learning of Generative Topic Saliency for Person Re-identification2014
- Dorsal and Ventral Attention SystemsThe Neuroscientist, 2013
- Unsupervised Salience Learning for Person Re-identification2013
- Tensor Decompositions and ApplicationsSIAM Review, 2009
- Contextual guidance of eye movements and attention in real-world scenes: The role of global features in object search.Psychological Review, 2006
- Regularized multi--task learning2004
- Optimal Brain Surgeon and general network pruning2002
- Introduction to AlgorithmsJournal of the Operational Research Society, 1991
- Forest before trees: The precedence of global features in visual perceptionCognitive Psychology, 1977