Signal Processing
Signal Processing
复制标题
DOI：
10.23919/mixdes.2018.8436682
复制
发表时间：
2013-05
期刊：
影响因子：
--
通讯作者：
Fredrik Gustafsson;Lennart Ljung;M. Millnert
中科院分区：
文献类型：
--
作者：
Fredrik Gustafsson;Lennart Ljung;M. Millnert
利用可学习的上采样策略DUppsampling代替常用的双线性插值，提高分割精度。我们部署了详细的实验上三个公开可用的数据集，命名为NWPU_YRCC_EX，NWPU_YRCC2，和阿尔伯塔河冰分割数据集。实验结果表明，我们的方法达到了最先进的性能与竞争方法，在NWPU_YRCC_EX数据集上，我们可以实现分割速度为90.84 FPS和分割精度为90.770% mIoU，这也说明了准确性和速度之间的良好平衡。我们的代码可在https://github.com/nwpulab113/FastICENet上获得 ©
learnable upsampling strategy DUpsampling is utilized to replace the commonly used bilinear interpolation to improve the segmentation accuracy. We deploy detailed experiments on three publicly available datasets, named NWPU_YRCC_EX, NWPU_YRCC2, and Alberta River Ice Segmentation Dataset. The experimental results demonstrate that our method achieves state-of-the-art performance with competing methods, on the NWPU_YRCC_EX dataset, we can achieve the segmentation speed as 90.84FPS and the segmentation accuracy as 90.770 % mIoU, which also illustrates the good leverage between accuracy and speed. Our code is available at https://github.com/nwpulab113/FastICENet ©