Identity Adaptation for Person Re-Identification
MetadataShow full item record
© 2013 IEEE. Person re-identification (re-ID), which aims to identify the same individual from a gallery collected with different cameras, has attracted increasing attention in the multimedia retrieval community. Current deep learning methods for person re-ID focus on learning classification models on training identities to obtain an ID-discriminative embedding (IDE) extractor, which is used to extract features from testing images for re-ID. The IDE features of the testing identities might not be discriminative due to that the training identities are different from the testing identities. In this paper, we introduce a new ID-adaptation network (ID-AdaptNet), which aims to improve the discriminative power of the IDE features of the testing identities for better person re-ID. The main idea of the ID-AdaptNet is to transform the IDE features to a common discriminative latent space, where the representations of the 'seen' training identities are enforced to adapt to those of the 'unseen' training identities. More specifically, the ID-AdaptNet is trained by simultaneously minimizing the classification cross-entropy and the discrepancy between the 'seen' and the 'unseen' training identities in the hidden space. To calculate the discrepancy, we represent their probability distributions as moment sequences and calculate their distance using their central moments. We further propose a stacking ID-AdaptNet that jointly trains multiple ID-AdaptNets with a regularization method for better re-ID. Experiments show that the ID-AdaptNet and stacking ID-AdaptNet effectively improve the discriminative power of IDE features.
Showing items related by title, author, creator and subject.
Moral choice in an agency framework and related motivational typologies as impacted by personal and contextual factors for financial institutions in China.Woodbine, Gordon F. (2002)In this study an empirical investigation is conducted of the factors affecting moral choice, a necessary antecedent to moral behaviour (or action). The theoretical framework has drawn upon Rest's (1983, 1986) model of ...
Mental health disparities within the LGBT population: A comparison between transgender and nontransgender individualsSu, D.; Irwin, J.; Fisher, Christopher; Ramos, A.; Kelley, M.; Rogel-Mednoza, D.; Coleman, J. (2016)Purpose: This study assessed within a Midwestern LGBT population whether, and the extent to which, transgender identity was associated with elevated odds of reported discrimination, depression symptoms, and suicide attempts. ...
Face recognition via local preserving average neighbourhood margin maximization and extreme learning machineChen, Xiaoming; Liu, Wan-Quan; Lai, J.; Li, Z.; Lu, C. (2012)Average neighborhood maximum margin (ANMM) is an effective method for feature extraction in appearance-based face recognition. In this paper, we extend ANMM to locality preserving average neighborhood margin maximization ...