Deep Neural Networks Regularization for Structured Output Prediction

04/28/2015
by   Soufiane Belharbi, et al.
0

A deep neural network model is a powerful framework for learning representations. Usually, it is used to learn the relation x → 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 → 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.

READ FULL TEXT

page 2

page 8

page 11

page 12

research
09/06/2017

Neural Networks Regularization Through Class-wise Invariant Representation Learning

Training deep neural networks is known to require a large number of trai...
research
07/21/2022

Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives

Recently, Implicit Neural Representations (INRs) parameterized by neural...
research
09/20/2020

Provable Finite Data Generalization with Group Autoencoder

Deep Autoencoders (AEs) provide a versatile framework to learn a compres...
research
07/07/2020

Soft Labeling Affects Out-of-Distribution Detection of Deep Neural Networks

Soft labeling becomes a common output regularization for generalization ...
research
04/29/2015

A Deep Learning Model for Structured Outputs with High-order Interaction

Many real-world applications are associated with structured data, where ...
research
01/25/2022

Neuro-Symbolic Entropy Regularization

In structured prediction, the goal is to jointly predict many output var...
research
02/15/2018

Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction

Structured prediction is concerned with predicting multiple inter-depend...

Please sign up or login with your details

Forgot password? Click here to reset