论文标题
抑制与平衡：一个简单的封闭式网络，用于显着对象检测
Suppress and Balance: A Simple Gated Network for Salient Object Detection
论文作者
论文摘要
大多数显着对象检测方法使用U-NET或功能金字塔网络（FPN）作为其基本结构。当编码器与解码器交换信息时，这些方法忽略了两个关键问题：一种是它们之间缺乏干扰控制，另一种是没有考虑不同编码器块的贡献的差异。在这项工作中，我们提出了一个简单的封闭式网络（Gatenet），以一次解决这两个问题。借助多级门单元，可以将来自编码器的宝贵上下文信息最佳地传输到解码器。我们设计了一种新颖的封闭式双分支结构，以在不同级别的特征之间建立合作，并提高整个网络的可区分性。通过双分支设计，可以进一步恢复显着性图的更多详细信息。此外，我们基于提出的“折叠”操作（fold-aspp）采用了非常空间的金字塔池，以准确定位各种尺度的显着对象。在五个具有挑战性的数据集上进行的广泛实验表明，所提出的模型对不同评估指标下的大多数最先进方法的性能有利。
Most salient object detection approaches use U-Net or feature pyramid networks (FPN) as their basic structures. These methods ignore two key problems when the encoder exchanges information with the decoder: one is the lack of interference control between them, the other is without considering the disparity of the contributions of different encoder blocks. In this work, we propose a simple gated network (GateNet) to solve both issues at once. With the help of multilevel gate units, the valuable context information from the encoder can be optimally transmitted to the decoder. We design a novel gated dual branch structure to build the cooperation among different levels of features and improve the discriminability of the whole network. Through the dual branch design, more details of the saliency map can be further restored. In addition, we adopt the atrous spatial pyramid pooling based on the proposed "Fold" operation (Fold-ASPP) to accurately localize salient objects of various scales. Extensive experiments on five challenging datasets demonstrate that the proposed model performs favorably against most state-of-the-art methods under different evaluation metrics.
