Cascade Network with Guided Loss and Hybrid Attention for Two-view Geometry
This work addresses the problem of improving geometric matching accuracy in computer vision, though it appears incremental as it builds on existing methods with specific enhancements.
The paper tackles two-view geometry by proposing a cascade network with a Guided Loss that directly optimizes Fn-measure and a hybrid attention block combining BACN and CA, achieving state-of-the-art performance on benchmark datasets.
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.