Deep Neural Networks Regularization for Structured Output Prediction

TL;DR

This paper introduces a regularization method for deep neural networks that enhances structured output prediction by learning output dependencies in an unsupervised manner, demonstrated on facial landmark detection tasks.

Contribution

It proposes a novel regularization scheme using a multi-task framework to incorporate output structure learning during neural network training.

Findings

Improves generalization of deep neural networks on structured output tasks.

Accelerates training of neural networks for structured prediction.

Utilizes unlabeled data to further enhance performance.

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.