论文标题
正规化密集连接的金字塔网络，用于显着实例分割
Regularized Densely-connected Pyramid Network for Salient Instance Segmentation
论文作者
论文摘要
最近在显着对象检测（SOD）上的许多努力都致力于生成准确的显着性图，而不意识到其实例标签。为此，我们为端到端的显着实例分割（SIS）提出了一条新的管道，该管道可预测每个检测到的显着实例的类不足的掩码。为了更好地使用深网中的丰富特征层次结构并增强了侧面预测，我们提出了正则密集的连接，这些连接良好地促进了信息的特征并抑制了所有特征金字塔的非信息性。引入了一种新型的基于多层皇家皇家基金的解码器，以适应汇总多层次特征，以获得更好的掩模预测。这些策略可以很好地塑造到面具R-CNN管道中。关于流行基准测试的广泛实验表明，我们的设计在AP度量方面显着优于现有的\ SART竞争对手6.3 \％（58.6 \％vs. 52.3 \％）。
Much of the recent efforts on salient object detection (SOD) have been devoted to producing accurate saliency maps without being aware of their instance labels. To this end, we propose a new pipeline for end-to-end salient instance segmentation (SIS) that predicts a class-agnostic mask for each detected salient instance. To better use the rich feature hierarchies in deep networks and enhance the side predictions, we propose the regularized dense connections, which attentively promote informative features and suppress non-informative ones from all feature pyramids. A novel multi-level RoIAlign based decoder is introduced to adaptively aggregate multi-level features for better mask predictions. Such strategies can be well-encapsulated into the Mask R-CNN pipeline. Extensive experiments on popular benchmarks demonstrate that our design significantly outperforms existing \sArt competitors by 6.3\% (58.6\% vs. 52.3\%) in terms of the AP metric.The code is available at https://github.com/yuhuan-wu/RDPNet.
