• 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 >Learning Pixel-Level Semantic Affinity with Image-Level Supervision for Weakly Supervised Semantic Segmentation
【24h】

Learning Pixel-Level Semantic Affinity with Image-Level Supervision for Weakly Supervised Semantic Segmentation

机译：通过图像级监督学习像素级语义亲和度以实现弱监督语义分割

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

摘要

The deficiency of segmentation labels is one of the main obstacles to semantic segmentation in the wild. To alleviate this issue, we present a novel framework that generates segmentation labels of images given their image-level class labels. In this weakly supervised setting, trained models have been known to segment local discriminative parts rather than the entire object area. Our solution is to propagate such local responses to nearby areas which belong to the same semantic entity. To this end, we propose a Deep Neural Network (DNN) called AffinityNet that predicts semantic affinity between a pair of adjacent image coordinates. The semantic propagation is then realized by random walk with the affinities predicted by AffinityNet. More importantly, the supervision employed to train AffinityNet is given by the initial discriminative part segmentation, which is incomplete as a segmentation annotation but sufficient for learning semantic affinities within small image areas. Thus the entire framework relies only on image-level class labels and does not require any extra data or annotations. On the PASCAL VOC 2012 dataset, a DNN learned with segmentation labels generated by our method outperforms previous models trained with the same level of supervision, and is even as competitive as those relying on stronger supervision.
机译：分割标签的不足是野外语义分割的主要障碍之一。为缓解此问题，我们提出了一个新颖的框架，该框架根据给定的图像级类标签生成图像的分割标签。在这种弱监督的情况下，已知训练有素的模型可以分割局部区分部分，而不是整个对象区域。我们的解决方案是将此类本地响应传播到属于同一语义实体的附近区域。为此，我们提出了一种称为AffinityNet的深度神经网络（DNN），该网络可预测一对相邻图像坐标之间的语义相似性。然后，通过具有AffinityNet预测的亲和力的随机游走来实现语义传播。更重要的是，用于训练AffinityNet的监督是由最初的区分部分分割提供的，该分割不完整，不能作为分割注释，但足以学习小图像区域内的语义关联。因此，整个框架仅依赖于图像级别的类标签，不需要任何额外的数据或注释。在PASCAL VOC 2012数据集上，使用我们的方法生成的分割标签学习的DNN优于以前在相同监督水平下训练的模型，甚至与依赖更强监督的模型一样具有竞争力。

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