A Comprehensive Analysis of Deep Regression - Archive ouverte HAL Access content directly
Journal Articles IEEE Transactions on Pattern Analysis and Machine Intelligence Year : 2020

A Comprehensive Analysis of Deep Regression

(1) , (1) , (1) , (1)
1

Abstract

Deep learning revolutionized data science, and recently its popularity has grown exponentially, as did the amount of papers employing deep networks. Vision tasks, such as human pose estimation, did not escape from this trend. There is a large number of deep models, where small changes in the network architecture, or in the data pre-processing, together with the stochastic nature of the optimization procedures, produce notably different results, making extremely difficult to sift methods that significantly outperform others. This situation motivates the current study, in which we perform a systematic evaluation and statistical analysis of vanilla deep regression, i.e. convolutional neural networks with a linear regression top layer. This is the first comprehensive analysis of deep regression techniques. We perform experiments on four vision problems, and report confidence intervals for the median performance as well as the statistical significance of the results, if any. Surprisingly, the variability due to different data pre-processing procedures generally eclipses the variability due to modifications in the network architecture. Our results reinforce the hypothesis according to which, in general, a general-purpose network (e.g. VGG-16 or ResNet-50) adequately tuned can yield results close to the state-of-the-art without having to resort to more complex and ad-hoc regression models.
Fichier principal
Vignette du fichier
main.pdf (3.2 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01754839 , version 1 (15-04-2019)

Identifiers

Cite

Stéphane Lathuilière, Pablo Mesejo, Xavier Alameda-Pineda, Radu Horaud. A Comprehensive Analysis of Deep Regression. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42 (9), pp.2065-2081. ⟨10.1109/TPAMI.2019.2910523⟩. ⟨hal-01754839⟩
849 View
466 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More