arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.11048cs.CV
收藏

显著目标检测的标签解耦框架

Label Decoupling Framework for Salient Object Detection

Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS(中国科学院计算技术研究所智能信息处理重点实验室);University of Chinese Academy of Sciences(中国科学院大学);Peng Cheng Laboratory(鹏城实验室);Kingsoft Cloud(金山云);Noah’s Ark Lab, Huawei Technologies(华为技术有限公司诺亚方舟实验室)

Jun Wei, Shuhui Wang, Zhe Wu, Chi Su, Qingming Huang, Qi Tian

摘要:

为了获得更准确的显著性图,最近的方法主要集中在聚合来自全卷积网络(FCN)的多层特征并引入边缘信息作为辅助监督。虽然已经取得了显着的进展,我们观察到,越接近边缘的像素,它是越难以预测,因为边缘像素有一个非常不平衡的分布。为了解决这个问题,我们提出了一个标签解耦框架(LDF),它由一个标签解耦(LD)过程和一个功能交互网络(FIN)。LD显式地将原始显着图分解为主体图和细节图,其中主体图集中在对象的中心区域,细节图集中在边缘周围的区域。细节图的效果更好,因为它比传统的边缘监督涉及更多的像素。与显著图不同的是,体图丢弃边缘像素,只关注中心区域。这成功地避免了训练过程中边缘像素的干扰。因此,我们使用FIN中的两个分支来分别处理身体图和细节图。特征交互(FI)的目的是融合这两个互补的分支,以预测显着图,然后使用它来细化这两个分支。这种迭代细化有助于学习更好的表示和更精确的显着图。在六个基准数据集上的综合实验表明,LDF在不同的评估指标上优于最先进的方法。

英文摘要:

To get more accurate saliency maps, recent methods mainly focus on aggregating multi-level features from fully convolutional network (FCN) and introducing edge information as auxiliary supervision. Though remarkable progress has been achieved, we observe that the closer the pixel is to the edge, the more difficult it is to be predicted, because edge pixels have a very imbalance distribution. To address this problem, we propose a label decoupling framework (LDF) which consists of a label decoupling (LD) procedure and a feature interaction network (FIN). LD explicitly decomposes the original saliency map into body map and detail map, where body map concentrates on center areas of objects and detail map focuses on regions around edges. Detail map works better because it involves much more pixels than traditional edge supervision. Different from saliency map, body map discards edge pixels and only pays attention to center areas. This successfully avoids the distraction from edge pixels during training. Therefore, we employ two branches in FIN to deal with body map and detail map respectively. Feature interaction (FI) is designed to fuse the two complementary branches to predict the saliency map, which is then used to refine the two branches again. This iterative refinement is helpful for learning better representations and more precise saliency maps. Comprehensive experiments on six benchmark datasets demonstrate that LDF outperforms state-of-the-art approaches on different evaluation metrics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑