<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Self-supervised monocular depth estimation has been widely applied in autonomous driving and automated guided vehicles. It offers the advantages of low cost and extended effective distance compared with alternative methods. However, like automated guided vehicles, devices with limited computing resources struggle to leverage state-of-the-art large model structures. In recent years, researchers have acknowledged this issue and endeavored to reduce model size. Model lightweight techniques aim to decrease the number of parameters while maintaining satisfactory performance. In this paper, to enhance the model’s performance in lightweight scenarios, a novel approach to encompassing three key aspects is proposed: (1) utilizing LeakyReLU to involve more neurons in manifold representation; (2) employing large convolution for improved recognition of edges in lightweight models; (3) applying channel grouping and shuffling to maximize the model efficiency. Experimental results demonstrate that our proposed method achieves satisfactory outcomes on KITTI and Make3D benchmarks while having only 1.6M trainable parameters, representing a reduction of 27% compared with the previous smallest model, Lite-Mono-tiny, in monocular depth estimation.</p>
</abstract>

Self-supervised monocular depth estimation has been widely applied in autonomous driving and automated guided vehicles. It offers the advantages of low cost and extended effective distance compared with alternative methods. However, like automated guided vehicles, devices with limited computing resources struggle to leverage state-of-the-art large model structures. In recent years, researchers have acknowledged this issue and endeavored to reduce model size. Model lightweight techniques aim to decrease the number of parameters while maintaining satisfactory performance. In this paper, to enhance the model’s performance in lightweight scenarios, a novel approach to encompassing three key aspects is proposed: (1) utilizing LeakyReLU to involve more neurons in manifold representation; (2) employing large convolution for improved recognition of edges in lightweight models; (3) applying channel grouping and shuffling to maximize the model efficiency. Experimental results demonstrate that our proposed method achieves satisfactory outcomes on KITTI and Make3D benchmarks while having only 1.6M trainable parameters, representing a reduction of 27% compared with the previous smallest model, Lite-Mono-tiny, in monocular depth estimation.

Shufflemono: Rethinking Lightweight Network for Self-Supervised Monocular Depth Estimation

Journal of Artificial Intelligence and Soft Computing Research

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Self-supervised monocular depth estimation has been widely applied in autonomous driving and automated guided vehicles. It offers the advantages of low cost...

Shufflemono: Rethinking Lightweight Network for Self-Supervised Monocular Depth Estimation

Online veröffentlicht: 11. Juni 2024

Seitenbereich: 191 - 205

Eingereicht: 11. Dez. 2023

Akzeptiert: 27. Feb. 2024

DOI: https://doi.org/10.2478/jaiscr-2024-0011

Schlüsselwörter
lightweight, self-supervised learning, depth estimation, monocular

© 2024 Yingwei Feng et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Shufflemono: Rethinking Lightweight Network for Self-Supervised Monocular Depth Estimation

Online veröffentlicht: 11. Juni 2024

Seitenbereich: 191 - 205

Eingereicht: 11. Dez. 2023

Akzeptiert: 27. Feb. 2024

DOI: https://doi.org/10.2478/jaiscr-2024-0011

Schlüsselwörterlightweight, self-supervised learning, depth estimation, monocular

© 2024 Yingwei Feng et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Schlüsselwörter
lightweight, self-supervised learning, depth estimation, monocular