Detail View

Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation
Citations

WEB OF SCIENCE

Citations

SCOPUS

Metadata Downloads

Title
Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation
Issued Date
2023-02-12
Citation
Bae, Jinwoo. (2023-02-12). Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation. AAAI Conference on Artificial Intelligence, 187–196. doi: 10.1609/aaai.v37i1.25090
Type
Conference Paper
ISBN
9781577358800
ISSN
2374-3468
Abstract
Self-supervised monocular depth estimation has been widely studied recently. Most of the work has focused on improving performance on benchmark datasets, such as KITTI, but has offered a few experiments on generalization performance. In this paper, we investigate the backbone networks (e.g. CNNs, Transformers, and CNN-Transformer hybrid models) toward the generalization of monocular depth estimation. We first evaluate state-of-the-art models on diverse public datasets, which have never been seen during the network training. Next, we investigate the effects of texture-biased and shape-biased representations using the various texture-shifted datasets that we generated. We observe that Transformers exhibit a strong shape bias and CNNs do a strong texture-bias. We also find that shape-biased models show better generalization performance for monocular depth estimation compared to texture-biased models. Based on these observations, we newly design a CNN-Transformer hybrid network with a multi-level adaptive feature fusion module, called MonoFormer. The design intuition behind MonoFormer is to increase shape bias by employing Transformers while compensating for the weak locality bias of Transformers by adaptively fusing multi-level representations. Extensive experiments show that the proposed method achieves state-of-the-art performance with various public datasets. Our method also shows the best generalization ability among the competitive methods. Copyright © 2023, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
URI
http://hdl.handle.net/20.500.11750/46776
DOI
10.1609/aaai.v37i1.25090
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Show Full Item Record

File Downloads

  • There are no files associated with this item.

공유

qrcode
공유하기

Related Researcher

임성훈
Im, Sunghoon임성훈

Department of Electrical Engineering and Computer Science

read more

Total Views & Downloads