论文标题
RRL：卷积神经网络中的区域旋转层
RRL:Regional Rotation Layer in Convolutional Neural Networks
论文作者
论文摘要
近年来，卷积神经网络（CNN）在图像分类和对象检测方面表现出色，但即使是最先进的模型也具有有限的旋转不变性。已知的解决方案包括增强训练数据和通过将旋转模化特征合并的旋转不变性的增加。这些方法要么增加训练的工作量，要么增加模型参数的数量。为了解决这个问题，本文提出了一个可以插入现有网络的模块，并将旋转不变性直接纳入CNN的特征提取层中。该模块没有可学习的参数，也不会增加模型的复杂性。同时，只有通过训练直立数据，它才能在旋转的测试集上表现良好。这些优势将适用于很难获得直立样品或目标没有方向性的生物医学和天文学等领域。用Lenet-5，Resnet-18和Tiny-Yolov3评估我们的模块，我们获得了令人印象深刻的结果。
Convolutional Neural Networks (CNNs) perform very well in image classification and object detection in recent years, but even the most advanced models have limited rotation invariance. Known solutions include the enhancement of training data and the increase of rotation invariance by globally merging the rotation equivariant features. These methods either increase the workload of training or increase the number of model parameters. To address this problem, this paper proposes a module that can be inserted into the existing networks, and directly incorporates the rotation invariance into the feature extraction layers of the CNNs. This module does not have learnable parameters and will not increase the complexity of the model. At the same time, only by training the upright data, it can perform well on the rotated testing set. These advantages will be suitable for fields such as biomedicine and astronomy where it is difficult to obtain upright samples or the target has no directionality. Evaluate our module with LeNet-5, ResNet-18 and tiny-yolov3, we get impressive results.
