Learning Non-linear Reconstruction Models for Image Set Classification
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1915-1922
Abstract
We propose a deep learning framework for image set classification with application to face recognition. An Adaptive Deep Network Template (ADNT) is defined whose parameters are initialized by performing unsupervised pre-training in a layer-wise fashion using Gaussian Restricted Boltzmann Machines (GRBMs). The pre-initialized ADNT is then separately trained for images of each class and class-specific models are learnt. Based on the minimum reconstruction error from the learnt class-specific models, a majority voting strategy is used for classification. The proposed framework is extensively evaluated for the task of image set classification based face recognition on Honda/UCSD, CMU Mobo, YouTube Celebrities and a Kinect dataset. Our experimental results and comparisons with existing state-of-the-art methods show that the proposed method consistently achieves the best performance on all these datasets.Keywords
This publication has 22 references indexed in Scilit:
- Automatic Feature Learning for Robust Shadow Detection2014
- Using Kinect for face recognition under varying poses, expressions, illumination and disguise2013
- Sparse approximated nearest points for image set classification2011
- Statistical Computations on Grassmann and Stiefel Manifolds for Image and Video-Based RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Incremental Learning for Robust Visual TrackingInternational Journal of Computer Vision, 2007
- Discriminative Learning and Recognition of Image Set Classes Using Canonical CorrelationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Unsupervised Discovery of Nonlinear Structure Using Contrastive BackpropagationCognitive Science, 2006
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Multiresolution gray-scale and rotation invariant texture classification with local binary patternsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002