• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops >MultiNet++: Multi-Stream Feature Aggregation and Geometric Loss Strategy for Multi-Task Learning
【24h】

MultiNet++: Multi-Stream Feature Aggregation and Geometric Loss Strategy for Multi-Task Learning

机译：MultInet ++：多行学习的多流特征聚合和几何损耗策略

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Multi-task learning is commonly used in autonomous driving for solving various visual perception tasks. It offers significant benefits in terms of both performance and computational complexity. Current work on multi-task learning networks focus on processing a single input image and there is no known implementation of multi-task learning handling a sequence of images. In this work, we propose a multi-stream multi-task network to take advantage of using feature representations from preceding frames in a video sequence for joint learning of segmentation, depth, and motion. The weights of the current and previous encoder are shared so that features computed in the previous frame can be leveraged without additional computation. In addition, we propose to use the geometric mean of task losses as a better alternative to the weighted average of task losses. The proposed loss function facilitates better handling of the difference in convergence rates of different tasks. Experimental results on KITTI, Cityscapes and SYNTHIA datasets demonstrate that the proposed strategies outperform various existing multi-task learning solutions.
机译：多任务学习通常用于自主驾驶，以解决各种视觉感知任务。它在性能和计算复杂性方面提供了显着的好处。当前关于多任务学习网络的工作专注于处理单个输入图像，并且没有已知实现多任务学习处理一系列图像的实现。在这项工作中，我们提出了一种多流多任务网络，以利用视频序列中的前面帧中的特征表示来利用用于共同学习分割，深度和运动的联合学习。共享当前和先前编码器的权重，从而可以利用在前一帧中计算的特征而无需额外计算。此外，我们建议使用任务损失的几何平均值作为任务损失的加权平均值的更好的替代方案。该损失功能有助于更好地处理不同任务的收敛率差异。基蒂，城市景观和合成足数据集的实验结果表明，拟议的策略优于各种现有的多任务学习解决方案。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号