MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification

07/25/2019
by   Lukas Liebel, et al.
12

We introduce MultiDepth, a novel training strategy and convolutional neural network (CNN) architecture that allows approaching single-image depth estimation (SIDE) as a multi-task problem. SIDE is an important part of road scene understanding. It, thus, plays a vital role in advanced driver assistance systems and autonomous vehicles. Best results for the SIDE task so far have been achieved using deep CNNs. However, optimization of regression problems, such as estimating depth, is still a challenging task. For the related tasks of image classification and semantic segmentation, numerous CNN-based methods with robust training behavior have been proposed. Hence, in order to overcome the notorious instability and slow convergence of depth value regression during training, MultiDepth makes use of depth interval classification as an auxiliary task. The auxiliary task can be disabled at test-time to predict continuous depth values using the main regression branch more efficiently. We applied MultiDepth to road scenes and present results on the KITTI depth prediction dataset. In experiments, we were able to show that end-to-end multi-task learning with both, regression and classification, is able to considerably improve training and yield more accurate results.

READ FULL TEXT

page 1

page 4

page 7

research
05/16/2018

Auxiliary Tasks in Multi-task Learning

Multi-task convolutional neural networks (CNNs) have shown impressive re...
research
05/09/2018

Deep 2.5D Vehicle Classification with Sparse SfM Depth Prior for Automated Toll Systems

Automated toll systems rely on proper classification of the passing vehi...
research
03/31/2023

Single Image Depth Prediction Made Better: A Multivariate Gaussian Take

Neural-network-based single image depth prediction (SIDP) is a challengi...
research
12/12/2019

Inferring Distributions Over Depth from a Single Image

When building a geometric scene understanding system for autonomous vehi...
research
02/22/2019

Towards end-to-end pulsed eddy current classification and regression with CNN

Pulsed eddy current (PEC) is an effective electromagnetic non-destructiv...
research
11/07/2018

Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks

The training of many existing end-to-end steering angle prediction model...

Please sign up or login with your details

Forgot password? Click here to reset