论文标题
超越单阶段编码器 - 码头网络：用于语义图像分割的深度解码器
Beyond Single Stage Encoder-Decoder Networks: Deep Decoders for Semantic Image Segmentation
论文作者
论文摘要
语义分割的单一编码器方法学方法在分割质量和效率每层数量方面达到了峰值。为了解决这些限制，我们建议基于解码器的新体系结构，该解码器使用一组浅网络来捕获更多信息内容。新的解码器具有跳过连接的新拓扑，即向后堆叠剩余连接。为了进一步改善体系结构，我们引入了一个重量函数，旨在重新平衡类，以增加网络的注意力对代表性不足的对象。我们进行了一系列广泛的实验，为Camvid，Gatech和Freiburg森林数据集提供了最先进的结果。此外，为了进一步证明解码器的有效性，我们进行了一系列实验，研究了解码器对最先进的分割技术的影响。此外，我们提出了一组实验，通过光流信息增强语义分割，表明运动线索可以促进基于图像的纯语义分割方法。
Single encoder-decoder methodologies for semantic segmentation are reaching their peak in terms of segmentation quality and efficiency per number of layers. To address these limitations, we propose a new architecture based on a decoder which uses a set of shallow networks for capturing more information content. The new decoder has a new topology of skip connections, namely backward and stacked residual connections. In order to further improve the architecture we introduce a weight function which aims to re-balance classes to increase the attention of the networks to under-represented objects. We carried out an extensive set of experiments that yielded state-of-the-art results for the CamVid, Gatech and Freiburg Forest datasets. Moreover, to further prove the effectiveness of our decoder, we conducted a set of experiments studying the impact of our decoder to state-of-the-art segmentation techniques. Additionally, we present a set of experiments augmenting semantic segmentation with optical flow information, showing that motion clues can boost pure image based semantic segmentation approaches.
