Semi-supervised deep learning for object tracking and classification
Authors:
- 1 October 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15224880,p. 848-852
Abstract
A semi-supervised deep learning paradigm is proposed for object classification/tracking. The method addresses the main difficulties of deep learning, by allowing unsupervised data to initially configure the network and then a gradient descent optimization scheme is triggered to fine tune the data. Unsupervised learning transforms the input data into smaller and more abstract forms of representations and therefore improves the stability, convergence and performance of the model. Additionally, an adaptive approach is presented in a way to allow dynamic modification of the model to the current visual conditions. Adaptation is performed by exploiting both unsupervised and supervised samples, coming by the application of a combined motion/deep learning tracker activating only at frames a decision mechanisms ascertains retraining.Keywords
This publication has 15 references indexed in Scilit:
- Scaling Up Spike-and-Slab Models for Unsupervised Feature LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Transforming Auto-Encoders2011
- Deep Learning and Its Applications to Signal and Information Processing [Exploratory DSPIEEE Signal Processing Magazine, 2010
- Stacks of convolutional Restricted Boltzmann Machines for shift-invariant feature learning2009
- Extracting and composing robust features with denoising autoencoders2008
- An empirical evaluation of deep architectures on problems with many factors of variation2007
- Restricted Boltzmann machines for collaborative filtering2007
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998