论文标题
级联网络具有指导性损失和混合注意力的两种视角几何形状
Cascade Network with Guided Loss and Hybrid Attention for Two-view Geometry
论文作者
论文摘要
在本文中，我们致力于设计一个高性能网络，以进行两视图几何。我们首先提出指导性损失，理论上通过动态调整训练过程中正和负类的权重，从而在损失和FN量之间建立直接负相关，以便始终对网络朝着增加FN量化的方向进行训练。通过这种方式，网络可以维持跨膜片损失的优势，同时最大程度地提高FN量度。然后，我们提出了一个混合注意力块来提取特征，该特征将贝叶斯的细心环境归一化（BACN）和渠道注意力（CA）集成。 BAC可以挖掘先前的信息以更好地利用全球环境，而CA可以捕获复杂的通道上下文，以增强网络的渠道意识。最后，基于我们的指导损失和混合注意力块，级联网络旨在逐步优化结果，以提高性能。实验表明，我们的网络在基准数据集上实现了最新性能。
In this paper, we are committed to designing a high-performance network for two-view geometry. We first propose a Guided Loss and theoretically establish the direct negative correlation between the loss and Fn-measure by dynamically adjusting the weights of positive and negative classes during training, so that the network is always trained towards the direction of increasing Fn-measure. By this way, the network can maintain the advantage of the cross-entropy loss while maximizing the Fn-measure. We then propose a hybrid attention block to extract feature, which integrates the bayesian attentive context normalization (BACN) and channel-wise attention (CA). BACN can mine the prior information to better exploit global context and CA can capture complex channel context to enhance the channel awareness of the network. Finally, based on our Guided Loss and hybrid attention block, a cascade network is designed to gradually optimize the result for more superior performance. Experiments have shown that our network achieves the state-of-the-art performance on benchmark datasets.
