Bidirectional Attention Network for Monocular Depth Estimation

Bidirectional Attention Network for Monocular Depth Estimation

In this paper, we propose a Bidirectional Attention Network (BANet), an end-to-end framework for monocular depth estimation (MDE) that addresses the limitation of effectively integrating local and global information in convolutional neural networks. The structure of this mechanism derives from a str...

Full description

Saved in:
Bibliographic Details
Published in:2021 IEEE International Conference on Robotics and Automation (ICRA) pp. 11746 - 11752
Main Authors: Aich, Shubhra, Uwabeza Vianney, Jean Marie, Amirul Islam, Md, Bingbing Liu, Mannat Kaur
Format: Conference Proceeding
Language:English
Published: IEEE 30-05-2021
Subjects:
Computational modeling
Conferences
Convolutional neural networks
Estimation
Machine translation
Memory management
Recurrent neural networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a Bidirectional Attention Network (BANet), an end-to-end framework for monocular depth estimation (MDE) that addresses the limitation of effectively integrating local and global information in convolutional neural networks. The structure of this mechanism derives from a strong conceptual foundation of neural machine translation, and presents a light-weight mechanism for adaptive control of computation similar to the dynamic nature of recurrent neural networks. We introduce bidirectional attention modules that utilize the feed-forward feature maps and incorporate the global context to filter out ambiguity. Extensive experiments reveal the high degree of capability of this bidirectional attention model over feed-forward baselines and other state-of-the-art methods for monocular depth estimation on two challenging datasets - KITTI and DIODE. We show that our proposed approach either outperforms or performs at least on a par with the state-of-the-art monocular depth estimation methods with less memory and computational complexity.
ISSN:2577-087X
DOI:10.1109/ICRA48506.2021.9560885