Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Robust optimization for deep regression
Author: Belagiannis, V.
Rupprecht, C.
Carneiro, G.
Navab, N.
Citation: Proceedings / IEEE International Conference on Computer Vision. IEEE International Conference on Computer Vision, 2015, vol.2015 International Conference on Computer Vision, ICCV 2015, pp.2830-2838
Publisher: IEEE
Issue Date: 2015
Series/Report no.: IEEE International Conference on Computer Vision
ISBN: 9781467383912
ISSN: 1550-5499
Conference Name: 2015 IEEE International Conference on Computer Vision (ICCV 2015) (11 Dec 2015 - 18 Dec 2015 : Santiago, CHILE)
Statement of
Vasileios Belagiannis, Christian Rupprecht, Gustavo Carneiro, and Nassir Navab
Abstract: Convolutional Neural Networks (ConvNets) have successfully contributed to improve the accuracy of regressionbased methods for computer vision tasks such as human pose estimation, landmark localization, and object detection. The network optimization has been usually performed with L2 loss and without considering the impact of outliers on the training process, where an outlier in this context is defined by a sample estimation that lies at an abnormal distance from the other training sample estimations in the objective space. In this work, we propose a regression model with ConvNets that achieves robustness to such outliers by minimizing Tukey's biweight function, an M-estimator robust to outliers, as the loss function for the ConvNet. In addition to the robust loss, we introduce a coarse-to-fine model, which processes input images of progressively higher resolutions for improving the accuracy of the regressed values. In our experiments, we demonstrate faster convergence and better generalization of our robust loss function for the tasks of human pose estimation and age estimation from face images. We also show that the combination of the robust loss function with the coarse-to-fine model produces comparable or better results than current state-of-the-art approaches in four publicly available human pose estimation datasets.
Keywords: Training, robustness, machine learning, convergence, minimization
Rights: © 2015 IEEE
DOI: 10.1109/ICCV.2015.324
Grant ID:
Published version:
Appears in Collections:Aurora harvest 8
Computer Science publications

Files in This Item:
File Description SizeFormat 
  Restricted Access
Restricted Access745.44 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.