用地理掩码增强时序建模，提升鸟瞰图分割精度
Geo-ConvGRU: Geographically Masked Convolutional Gated Recurrent Unit for Bird-Eye View Segmentation
- 用ConvGRU替代3D CNN，更好捕捉时间依赖性
- 引入地理掩码抑制时序模块噪声，提升稳定性
- 在NuScenes上达到领先性能，适合自动驾驶场景
卷积神经网络（CNN）在计算机视觉任务中影响深远，但因其卷积操作的局部性，难以显式建模长程依赖。尽管变换器（Transformers）解决了空间维度的长程依赖问题，但对时间维度的关注仍不足。本文首先指出3D CNN在捕捉长程时间依赖方面存在局限；虽变换器缓解了空间问题，却导致参数量显著增加且处理速度下降。为此，我们提出一种简单而有效的模块——地理掩码卷积门控循环单元（Geo-ConvGRU），专用于鸟瞰图分割。具体地，在时间模块中用ConvGRU替代3D CNN层，以增强网络处理时间依赖的能力；同时在卷积门控循环单元中引入地理掩码，抑制时间模块带来的噪声。在NuScenes数据集上的全面实验验证了所提方法的优势，结果表明该方法在鸟瞰图分割任务中达到了当前最优性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。