Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition
This paper explores multi-task learning (MTL) for face recognition. First, we propose a multi-task convolutional neural network (CNN) for face recognition, where identity classification is the main task and pose, illumination, and expression (PIE) estimations are the side tasks. Second, we develop a dynamic-weighting scheme to automatically assign the loss weights to each side task, which solves the crucial problem of balancing between different tasks in MTL. Third, we propose a pose-directed multi-task CNN by grouping different poses to learn pose-specific identity features, simultaneously across all poses in a joint framework. Last but not least, we propose an energy-based weight analysis method to explore how CNN-based MTL works. We observe that the side tasks serve as regularizations to disentangle the PIE variations from the learnt identity features. Extensive experiments on the entire multi-PIE dataset demonstrate the effectiveness of the proposed approach. To the best of our knowledge, this is the first work using all data in multi-PIE for face recognition. Our approach is also applicable to in-the-wild data sets for pose-invariant face recognition and achieves comparable or better performance than state of the art on LFW, CFP, and IJB-A datasets.
Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition.
This paper explores multi-task learning (MTL) for face recognition. First, we propose a multi-task convolutional neural network (CNN) for face recognition, where identity classification is the main task and pose, illumination, and expression (PIE) estimations are the side tasks. Second, we develop a dynamic-weighting scheme to automatically assign the loss weights to each side task, which solves the crucial problem of balancing between different tasks in MTL. Third, we propose a pose-directed multi-task CNN by grouping different poses to learn pose-specific identity features, simultaneously across all poses in a joint framework. Last but not least, we propose an energy-based weight analysis method to explore how CNN-based MTL works. We observe that the side tasks serve as regularizations to disentangle the PIE variations from the learnt identity features. Extensive experiments on the entire multi-PIE dataset demonstrate the effectiveness of the proposed approach. To the best of our knowledge, this is the first work using all data in multi-PIE for face recognition. Our approach is also applicable to in-the-wild data sets for pose-invariant face recognition and achieves comparable or better performance than state of the art on LFW, CFP, and IJB-A datasets.
neural network differential equation deep learning convolutional neural network convolutional neural software development deep neural network feature selection open source deep neural optical network learning approach geographic information system distributed generation geographic information stochastic differential equation power allocation open source software stochastic differential deep convolutional neural source software deep convolutional named entity recognition loss function human action space telescope personal area network mental health feature learning wireless personal area elastic optical multi-task learning personal area elastic optical network network reconfiguration wireless personal learning problem hubble space telescope learning task software developer high rate water pressure hubble space doubly stochastic open source tool source software development free and open capacity allocation low rate source software project group lasso path protection sparse learning backup path rate wireles open source gi spare capacity optimal reconfiguration source gi multi-task deep backward doubly stochastic doubly stochastic differential backward doubly big bang-big crunch low rate wireles survivable routing multi-task deep learning guidance sensor bang-big crunch big bang-big multi-task learning approach source software tool deep multi-task deep multi-task learning pose-invariant face high water pressure fine guidance shared backup fine guidance sensor multi-task convolutional neural multi-task learning model source gis software shared backup path multi-task feature bang-big crunch algorithm backup path protection approximating optimal crunch algorithm multi-task learning method software movement multi-task network spare capacity allocation multi-task convolutional multi-task cnn multi-task sparse multi-task feature learning multi-task regression multi-task allocation feature learning algorithm multiple related task multi-task multi-view multi-task learning algorithm soils contaminated