# Cascade Network with Guided Loss and Hybrid Attention for Finding Good Correspondences

arXiv: https://arxiv.org/abs/2102.00411 · HTML: https://mlsanity.com/paper/2102.00411/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 31 Jan 2021.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [YFCC100M: The New Data in Multimedia Research](https://mlsanity.com/paper/1503.01817/) (2015)
- [Working hard to know your neighbor's margins: Local descriptor learning loss](https://mlsanity.com/paper/1705.10872/) (2017)
- [Learning to Find Good Correspondences](https://mlsanity.com/paper/1711.05971/) (2017)
- [Learning Two-View Correspondences and Geometry Using Order-Aware Network](https://mlsanity.com/paper/1908.04964/) (2019)
- [Graph-Cut RANSAC](https://mlsanity.com/paper/1706.00984/) (2017)
- [Neural Nearest Neighbors Networks](https://mlsanity.com/paper/1810.12575/) (2018)
- [PixelLink: Detecting Scene Text via Instance Segmentation](https://mlsanity.com/paper/1801.01315/) (2018)
- [NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences](https://mlsanity.com/paper/1904.00320/) (2019)
- [Optimizing the F-measure for Threshold-free Salient Object Detection](https://mlsanity.com/paper/1805.07567/) (2018)
- [ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning](https://mlsanity.com/paper/1907.02545/) (2019)

## Built on by (most cited first, 2 of 2)

- [SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration](https://mlsanity.com/paper/2203.14453/) (2022)
- [DetarNet: Decoupling Translation and Rotation by Siamese Network for Point Cloud Registration](https://mlsanity.com/paper/2112.14059/) (2021)

## Abstract (arXiv)

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 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. Our code will be available in https://github.com/wenbingtao/GLHA.