当前位置: X-MOL 学术ACM Trans. Multimed. Comput. Commun. Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Residual Refinement Network with Attribute Guidance for Precise Saliency Detection
ACM Transactions on Multimedia Computing, Communications, and Applications ( IF 5.1 ) Pub Date : 2021-07-22 , DOI: 10.1145/3440694
Feng Lin 1 , Wengang Zhou 1 , Jiajun Deng 1 , Bin Li 2 , Yan Lu 2 , Houqiang Li 1
Affiliation  

As an important topic in the multimedia and computer vision fields, salient object detection has been researched for years. Recently, state-of-the-art performance has been witnessed with the aid of the fully convolutional networks (FCNs) and the various pyramid-like encoder-decoder frameworks. Starting from a common encoder-decoder architecture, we enhance a residual refinement network with feature purification for better saliency estimation. To this end, we improve the global knowledge streams with intermediate supervisions for global saliency estimation and design a specific feature subtraction module for residual learning, respectively. On the basis of the strengthened network, we also introduce an attribute encoding sub-network (AENet) with a grid aggregation block (GAB) to guide the final saliency predictor to obtain more accurate saliency maps. Furthermore, the network is trained with a novel constraint loss besides the traditional cross-entropy loss to yield the finer results. Extensive experiments on five public benchmarks show our method achieves better or comparable performance compared with previous state-of-the-art methods.

中文翻译:

用于精确显着性检测的带有属性指导的残差细化网络

作为多媒体和计算机视觉领域的一个重要课题,显着目标检测已被研究多年。最近,借助全卷积网络 (FCN) 和各种类似金字塔的编码器-解码器框架,见证了最先进的性能。从常见的编码器-解码器架构开始,我们通过特征纯化增强了残差细化网络,以实现更好的显着性估计。为此,我们通过中间监督来改进全局知识流以进行全局显着性估计,并分别为残差学习设计一个特定的特征减法模块。在加强网络的基础上,我们还引入了一个带有网格聚合块(GAB)的属性编码子网络(AENet)来指导最终的显着性预测器获得更准确的显着性图。此外,除了传统的交叉熵损失之外,网络还使用新的约束损失进行训练,以产生更好的结果。对五个公共基准的广泛实验表明,与以前的最先进方法相比,我们的方法取得了更好或相当的性能。
更新日期:2021-07-22
down
wechat
bug