Saved in:
Bibliographic Details
Main Authors: Yang, Guanglei, Zhang, Yongqiang, Li, Wanlong, Tang, Yu, Shang, Weize, Wen, Feng, Zhang, Hongbo, Ding, Mingli
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.20171
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909443824812032
author Yang, Guanglei
Zhang, Yongqiang
Li, Wanlong
Tang, Yu
Shang, Weize
Wen, Feng
Zhang, Hongbo
Ding, Mingli
author_facet Yang, Guanglei
Zhang, Yongqiang
Li, Wanlong
Tang, Yu
Shang, Weize
Wen, Feng
Zhang, Hongbo
Ding, Mingli
contents Convolutional Neural Networks (CNNs) have significantly impacted various computer vision tasks, however, they inherently struggle to model long-range dependencies explicitly due to the localized nature of convolution operations. Although Transformers have addressed limitations in long-range dependencies for the spatial dimension, the temporal dimension remains underexplored. In this paper, we first highlight that 3D CNNs exhibit limitations in capturing long-range temporal dependencies. Though Transformers mitigate spatial dimension issues, they result in a considerable increase in parameter and processing speed reduction. To overcome these challenges, we introduce a simple yet effective module, Geographically Masked Convolutional Gated Recurrent Unit (Geo-ConvGRU), tailored for Bird's-Eye View segmentation. Specifically, we substitute the 3D CNN layers with ConvGRU in the temporal module to bolster the capacity of networks for handling temporal dependencies. Additionally, we integrate a geographical mask into the Convolutional Gated Recurrent Unit to suppress noise introduced by the temporal module. Comprehensive experiments conducted on the NuScenes dataset substantiate the merits of the proposed Geo-ConvGRU, revealing that our approach attains state-of-the-art performance in Bird's-Eye View segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20171
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Geo-ConvGRU: Geographically Masked Convolutional Gated Recurrent Unit for Bird-Eye View Segmentation
Yang, Guanglei
Zhang, Yongqiang
Li, Wanlong
Tang, Yu
Shang, Weize
Wen, Feng
Zhang, Hongbo
Ding, Mingli
Computer Vision and Pattern Recognition
Convolutional Neural Networks (CNNs) have significantly impacted various computer vision tasks, however, they inherently struggle to model long-range dependencies explicitly due to the localized nature of convolution operations. Although Transformers have addressed limitations in long-range dependencies for the spatial dimension, the temporal dimension remains underexplored. In this paper, we first highlight that 3D CNNs exhibit limitations in capturing long-range temporal dependencies. Though Transformers mitigate spatial dimension issues, they result in a considerable increase in parameter and processing speed reduction. To overcome these challenges, we introduce a simple yet effective module, Geographically Masked Convolutional Gated Recurrent Unit (Geo-ConvGRU), tailored for Bird's-Eye View segmentation. Specifically, we substitute the 3D CNN layers with ConvGRU in the temporal module to bolster the capacity of networks for handling temporal dependencies. Additionally, we integrate a geographical mask into the Convolutional Gated Recurrent Unit to suppress noise introduced by the temporal module. Comprehensive experiments conducted on the NuScenes dataset substantiate the merits of the proposed Geo-ConvGRU, revealing that our approach attains state-of-the-art performance in Bird's-Eye View segmentation.
title Geo-ConvGRU: Geographically Masked Convolutional Gated Recurrent Unit for Bird-Eye View Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.20171