2021-12-07

translated by 谷歌翻译

2021-02-16

translated by 谷歌翻译

2021-11-07

translated by 谷歌翻译

2020-08-20
LIDAR数据的实时语义分割对于自动驾驶车辆至关重要，这通常配备有嵌入式平台并具有有限的计算资源。直接在点云上运行的方法使用复杂的空间聚合操作，这非常昂贵，难以优化嵌入式平台。因此，它们不适用于嵌入式系统的实时应用。作为替代方案，基于投影的方法更有效并且可以在嵌入式平台上运行。然而，目前基于最先进的投影的方法不会达到与基于点的方法相同的准确性并使用数百万个参数。因此，我们提出了一种基于投影的方法，称为多尺度交互网络（Minet），这是非常有效和准确的。该网络使用具有不同尺度的多个路径并余额尺度之间的计算资源。尺度之间的额外密集相互作用避免了冗余计算并使网络高效。在准确度，参数数量和运行时，所提出的网络以基于点为基础的基于图像和基于投影的方法。此外，网络处理在嵌入式平台上每秒超过24个扫描，该嵌入式平台高于激光雷达传感器的帧。因此，网络适用于自动车辆。
translated by 谷歌翻译

2021-08-06

translated by 谷歌翻译

2021-12-02

translated by 谷歌翻译

2020-08-10

translated by 谷歌翻译

2021-11-18

translated by 谷歌翻译

2020-09-17

translated by 谷歌翻译

2021-12-06

translated by 谷歌翻译

2021-11-26

translated by 谷歌翻译

2021-08-05

translated by 谷歌翻译

2021-04-10

translated by 谷歌翻译

2022-01-10

translated by 谷歌翻译
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixelsto-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build "fully convolutional" networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet [20], the VGG net [31], and GoogLeNet [32]) into fully convolutional networks and transfer their learned representations by fine-tuning [3] to the segmentation task. We then define a skip architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves stateof-the-art segmentation of PASCAL VOC (20% relative improvement to 62.2% mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes less than one fifth of a second for a typical image.
translated by 谷歌翻译

2021-11-25

translated by 谷歌翻译

2021-12-07

translated by 谷歌翻译

2021-11-24

translated by 谷歌翻译

2021-07-07

translated by 谷歌翻译

2022-01-03

translated by 谷歌翻译
\${authors}

\${pubdate}
\${abstract_cn}
translated by 谷歌翻译