Can I read Cascade Network with Guided Loss and Hybrid Attention for Finding Good Correspondences on EtoBox?

Cascade Network with Guided Loss and Hybrid Attention for Finding Good Correspondences by Chen, Zhi; Yang, Fan; Tao, Wenbing is a scholarly article available to read on EtoBox.

What is Cascade Network with Guided Loss and Hybrid Attention for Finding Good Correspondences about?

Finding good correspondences is a critical prerequisite in many feature based tasks. Given a putative correspondence set of an image pair, we propose a neural network which finds correct correspondences by a binary-class classifier and estimates relative pose through classified correspondences. First, we analyze that due to the imbalance in the number of correct and wrong correspondences, the loss function has a great impact on the classification results. Thus, we propose a new Guided Loss that can directly use evaluation criterion (Fn-measure) as guidance to dynamically adjust the objective function during training. We theoretically prove that the perfect negative correlation between the Guided Loss and Fn-measure, so that the network is always trained towards the direction of increasing Fn-measure to maximize it. 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 atte

Author

Chen, Zhi; Yang, Fan; Tao, Wenbing

Published

2021

Language

EN