Constructing a meta-tracker using Dropout to imitate the behavior of an arbitrary black-box tracker. (March 2017)

• Record Type: Journal Article
• Authors: Meshgi, Kourosh; Maeda, Shin-ichi; Oba, Shigeyuki; Ishii, Shin
• Is Part Of: Neural networks. Volume 87(2017)
• Page Start: 132
• Page End: 148
• Publication Date: 2017-03
• Subjects: Dropout -- Tracking -- Features selection -- Generalization; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2016.12.009
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Imitating the behaviors of an arbitrary visual tracking algorithm enables many higher level tasks such as tracker identification and efficient tracker-fusion. It is also useful for discovering the features essential in a black-box tracker or learning from several trackers to form a super-tracker. In this study, we propose a non-linear feature fusion framework, " MIMIC " that imitates many popular trackers by mixing a pool of heterogeneous features. The MIMIC framework consists of two subtasks, feature selection and feature weight tuning. These subtasks, however, tended to suffer from an overfitting problem when the number of videos available for training is limited. To address this issue, we incorporated Dropout algorithm into the training, which grants the trained MIMIC tracker a high degree of generalization. Extensive experiments testified the effectiveness of the proposed framework so that its applications would be promoted into different related tasks in visual tracking.