ID 原文 译文
38856 为了解决这些问题，本文提出了一种基于自注意力的多阶段无监督单目深度估计网络。 To tackle these problems, we propose a self-attention based multi-stage network for unsupervised monocular depth estimation.
38857 该方法具有以下特点: Our method incorporates the following features:
38858 1)多阶段网络结构对训练过程中的深度估计具有较强的约束和监督作用; 1) multi-stage network provides stronger constraint and supervision for depth estimation during training;
38859 2)通过掩模加权重构损失和左右视差一致性损失对网络进行优化; 2) the network is optimized with mask weighted reconstruction loss and left-right disparity consistency loss;
38860 3)采用自注意力机制捕捉更多上下文信息，进而提升预测结果。 3) self-attention module is adopted to capture more context information.
38861 实验结果表明，该方法在KITTI数据集上的深度估计效果达到甚至超过了已有方法。 Experimental results on the KITTI dataset show that the method can obtain state-of-the-art performance, which means the proposed method can effectively improve the performance of monocular depth estimation.
38862 交通标志检测技术是先进驾驶辅助系统中重要组成部分。 Traffic sign detection technology is an essential part of the advanced driving assistance system.
38863 真实的驾驶环境中要求交通标志检测系统具备极高的实时性与准确性。 The real-life driving environment requires the traffic sign detection system to have an extremely high real-time performance and accuracy.
38864 轻量级网络MobileNetv2-SSD能够满足检测的实时性，但准确性不足以满足实际需求。 Lightweight network MobileNetv2-SSD can satisfy real-time detection tasks, but the accuracy can not satisfy the actual requirement.
38865 本文将MobileNetv2-SSD作为基础网络，提出一种基于像素重排的多尺度像素特征融合方法，并在网络的检测层引入高效通道注意力机制，实现特征增强。 This paper takes MobileNetv2-SSD as the underlying network, proposed a multi-scale pixel feature fusion method based on pixel shuffle, and introduced an efficient channel attention mechanism at the network's detection layer to achieve feature enhancement.