首页> 外文期刊>IEEE Transactions on Image Processing >Semantic Image Segmentation by Scale-Adaptive Networks
【24h】

Semantic Image Segmentation by Scale-Adaptive Networks

机译:尺度自适应网络的语义图像分割

获取原文
获取原文并翻译 | 示例

摘要

Semantic image segmentation is an important yet unsolved problem. One of the major challenges is the large variability of the object scales. To tackle this scale problem, we propose a Scale-Adaptive Network (SAN) which consists of multiple branches with each one taking charge of the segmentation of the objects of a certain range of scales. Given an image, SAN first computes a dense scale map indicating the scale of each pixel which is automatically determined by the size of the enclosing object. Then the features of different branches are fused according to the scale map to generate the final segmentation map. To ensure that each branch indeed learns the features for a certain scale, we propose a scale-induced ground-truth map and enforce a scale-aware segmentation loss for the corresponding branch in addition to the final loss. Extensive experiments over the PASCAL-Person-Part, the PASCAL VOC 2012, and the Look into Person datasets demonstrate that our SAN can handle the large variability of the object scales and outperforms the state-of-the-art semantic segmentation methods.
机译:语义图像分割是一个重要的尚未解决的问题。其中一个主要挑战是对象尺度的巨大可变性。为了解决这个规模的问题,我们提出了一个规模 - 自适应网络(SAN),该网络(SAN)由多个分支组成,每个分支机构负责一定范围的尺度的对象的分割。给定图像,SAN首先计算指示由封闭对象的大小自动确定的每个像素的比例的密集刻度映射。然后根据刻度图融合不同分支的特征以生成最终的分割图。为确保每个分支确实了解一定规模的特征,我们提出了一个规模诱导的地面图,除了最终损失之外,除了最终损失之外,还强制执行相应分支的尺度感知分段损耗。对Pascal-Person部分的广泛实验 - 部分,Pascal VOC 2012,以及调查人员数据集表明,我们的SAN可以处理对象尺度的大变可变性,并且优于最先进的语义分段方法。

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