GLA-Net: An Attention Network with Guided Loss for Mismatch Removal
This work addresses mismatch removal, a critical step in feature-based tasks like computer vision, with incremental improvements to existing deep learning methods.
The paper tackles the class imbalance problem in deep learning-based mismatch removal by proposing a Guided Loss directly linked to Fn-score and introduces an Inlier Attention Block to address outlier impairment of global context, achieving state-of-the-art performance on benchmark datasets.
Mismatch removal is a critical prerequisite in many feature-based tasks. Recent attempts cast the mismatch removal task as a binary classification problem and solve it through deep learning based methods. In these methods, the imbalance between positive and negative classes is important, which affects network performance, i.e., Fn-score. To establish the link between Fn-score and loss, we propose to guide the loss with the Fn-score directly. We theoretically demonstrate the direct link between our Guided Loss and Fn-score during training. Moreover, we discover that outliers often impair global context in mismatch removal networks. To address this issue, we introduce the attention mechanism to mismatch removal task and propose a novel Inlier Attention Block (IA Block). To evaluate the effectiveness of our loss and IA Block, we design an end-to-end network for mismatch removal, called GLA-Net \footnote{Our code will be available in Github later.}. Experiments have shown that our network achieves the state-of-the-art performance on benchmark datasets.