Deep Neural Networks Regularization for Structured Output Prediction
Preprint
Abstract
A deep neural network model is a powerful framework for learning representations. Usually, it is used to learn the relation $x \to y$ by exploiting the regularities in the input $x$. In structured output prediction problems, $y$ is multi-dimensional and structural relations often exist between the dimensions. The motivation of this work is to learn the output dependencies that may lie in the output data in order to improve the prediction accuracy. Unfortunately, feedforward networks are unable to exploit the relations between the outputs. In order to overcome this issue, we propose in this paper a regularization scheme for training neural networks for these particular tasks using a multi-task framework. Our scheme aims at incorporating the learning of the output representation $y$ in the training process in an unsupervised fashion while learning the supervised mapping function $x \to y$. We evaluate our framework on a facial landmark detection problem which is a typical structured output task. We show over two public challenging datasets (LFPW and HELEN) that our regularization scheme improves the generalization of deep neural networks and accelerates their training. The use of unlabeled data and label-only data is also explored, showing an additional improvement of the results. We provide an opensource implementation (https://github.com/sbelharbi/structured-output-ae) of our framework.
Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes2017
- IODA: An input/output deep architecture for image labelingPattern Recognition, 2015
- Facial Landmark Detection by Deep Multi-task Learning2014
- Learning Hierarchical Features for Scene LabelingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Enzyme Function Prediction with Interpretable Models2009
- A Novel Connectionist System for Unconstrained Handwriting RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Coupling CRFs and Deformable Models for 3D Medical Image Segmentation2007
- A Markovian Approach for Handwritten Document Segmentation2006
- Contextual Recognition of Hand-Drawn Diagrams with Conditional Random Fields2004
- A statistical approach for phrase location and recognition within a text line: an application to street name recognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002