• 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 >Error Correction for Dense Semantic Image Labeling
【24h】

Error Correction for Dense Semantic Image Labeling

机译：密集语义图像标记的纠错

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

摘要

Pixel-wise semantic image labeling is an important, yet challenging task with many applications. Especially in autonomous driving systems, it allows for a full understanding of the system's surroundings, which is crucial for trajectory planning. Typical approaches to tackle this problem involve either the training of deep networks on vast amounts of images to directly infer the labels or the use of probabilistic graphical models to jointly model the dependencies of the input (i.e. images) and output (i.e. labels). Yet, the former approaches do not capture the structure of the output labels, which is crucial for the performance of dense labeling, and the latter rely on carefully hand-designed priors that require costly parameter tuning via optimization techniques, which in turn leads to long inference times. To alleviate these restrictions, we explore how to arrive at dense semantic pixel labels given both the input image and an initial estimate of the output labels. We propose a parallel architecture that: 1) exploits the context information through a LabelPropagation network to propagate correct labels from nearby pixels to improve the object boundaries, 2) uses a LabelReplacement network to directly replace possibly erroneous, initial labels with new ones, and 3) combines the different intermediate results via a Fusion network to obtain the final per-pixel label. We experimentally validate our approach on two different datasets for semantic segmentation, where we show improvements over the state-of-the-art. We also provide both a quantitative and qualitative analysis of the generated results.
机译：Pixel-Wise语义图像标记是许多应用程序的重要而挑战性的任务。特别是在自动驾驶系统中，它允许全面了解系统的周围环境，这对于轨迹规划至关重要。解决这个问题的典型方法涉及对大量图像上的深网络训练，直接推断标签或使用概率图形模型，共同模拟输入（即图像）和输出（即标签）的依赖关系。然而，前一种方法不会捕获输出标签的结构，这对于致密标签的性能至关重要，并且后者依赖于通过优化技术需要昂贵的手动参数调整的仔细手工设计的前沿，这反过来导致长度推理时间。为了减轻这些限制，我们探讨了如何给定输入图像和输出标签的初始估计给出致密语义像素标签。我们提出了一种并行架构，即：1）利用LabelPropagation网络利用上下文信息来从附近的像素传播正确的标签以改善对象边界，2）使用LabelReplacement网络直接替换有新的初始标签，以及3 ）通过融合网络组合不同的中间结果以获得最终的每个像素标签。我们通过在两个不同的数据集上实验验证了我们的语义细分，我们展示了最先进的。我们还提供对生成的结果的定量和定性分析。

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