当前位置: X-MOL 学术Neurocomputing › 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.)
GCCNet: Grouped Channel Composition Network for Scene Text Detection
Neurocomputing ( IF 5.5 ) Pub Date : 2021-05-05 , DOI: 10.1016/j.neucom.2021.04.095
Chang Liu , Chun Yang , Jie-Bo Hou , Long-Huang Wu , Xiao-Bin Zhu , Lei Xiao , Xu-Cheng Yin

Anchor mechanism is widely applied in scene text detection methods and demonstrates promising performance. However, existing anchor mechanisms have two major limitations, namely handcrafted anchor design and hard-wired anchor assignment. We propose a novel Grouped Channels Composition(GCC) block to achieve the data-driven anchor design and adaptive anchor assignment. To be more specific, our GCC block uses optimizable anchor functions rather than handcrafted ones to achieve data-drive anchor design. In our GCC block, an adaptive anchor assignment is achieved with the attention mechanism instead of empirically assigning anchor according to the Intersection Over Union (IoU) between ground truth and targets. We then build a corresponding network named GCCNet with our GCC blocks. We also propose a Unified Loss Weighting module to alleviate the inconsistency between classification score and localization accuracy. Experiments conducted on publicly available datasets demonstrate the state-of-the-art performance of our methods. keyword: Anchor, Scene Text Detection, Grouped Channel Composition Network



中文翻译:

GCCNet:用于场景文本检测的分组通道组合网络

锚机制在场景文本检测方法中得到了广泛的应用,并证明了其良好的性能。但是,现有的锚固机制有两个主要限制,即手工锚固设计和硬接线锚固分配。我们提出了一种新颖的分组信道合成(GCC)块,以实现数据驱动的锚设计和自适应锚分配。更具体地说,我们的GCC模块使用可优化的锚点功能而不是手工的功能来实现数据驱动器锚点设计。在我们的GCC区块中,通过注意力机制实现了自适应锚分配,而不是根据地面真相与目标之间的联合交集(IoU)经验分配锚。然后,我们使用我们的GCC块构建一个名为GCCNet的相应网络。我们还提出了统一损失加权模块,以减轻分类评分和定位精度之间的不一致。在公开可用的数据集上进行的实验证明了我们方法的最先进性能。关键字:锚点,场景文本检测,分组频道组成网络

更新日期:2021-05-05
down
wechat
bug