We introduce a novel approach for keypoint detection task that combines
handcrafted and learned CNN filters within a shallow multi-scale architecture.
Handcrafted filters provide anchor structures for learned filters, which
localize, score and rank repeatable features. Scale-space representation is
used within the network to extract keypoints at different levels. We design a
loss function to detect robust features that exist across a range of scales and
to maximize the repeatability score. Our Key.Net model is trained on data
synthetically created from ImageNet and evaluated on HPatches benchmark.
Results show that our approach outperforms state-of-the-art detectors in terms
of repeatability, matching performance and complexity.

介绍了一种新颖的关键点检测方法，该方法结合了手工制作和学习的 CNN 滤波器，使用浅层的多尺度架构，在网络中使用尺度空间表示，在不同的层面提取关键点，并设计了一种损失函数来最大化关键特征的可重复性，使用 ImageNet 数据集创建了合成数据用于训练并在 HPatches 基准测试中进行了评估，结果显示我们的方法在可重复性，匹配性能和复杂性方面优于现有的检测器。

Key.Net: 通过手工设计和学习卷积神经网络滤波器进行关键点检测

Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters

Typical convolutional neural networks (CNNs) have several millions of
parameters and require a large amount of annotated data to train them. In
medical applications where training data is hard to come by, these
sophisticated machine learning models are difficult to train. In this paper, we
propose a method to reduce the inherent complexity of CNNs during training by
exploiting the significant redundancy that is noticed in the learnt CNN
filters. Our method relies on finding a small set of filters and mixing
coefficients to derive every filter in each convolutional layer at the time of
training itself, thereby reducing the number of parameters to be trained. We
consider the problem of 3D lung nodule segmentation in CT images and
demonstrate the effectiveness of our method in achieving good results with only
few training examples.

本文介绍了一种在训练期间利用卷积神经网络（CNNs）中学习到的滤波器的显着冗余的方法，通过找到一组小滤波器和混合系数来推导每个卷积层中的每个滤波器，从而减少训练参数。作者使用 CT 图像进行 3D 肺结节分割，证明了该方法只需要少量训练例子即可获得良好的结果。