Abstract
Achieving rotation invariance in deep neural networks without relying on data has always been a hot research topic. Intrinsic rotation invariance can enhance the model's feature representation capability, enabling better performance in tasks such as multi-orientation object recognition and detection. Based on various types of non-learnable operators, including gradient, sort, local binary pattern, maximum, etc., this paper designs a set of new convolution operations that are natually invariant to arbitrary rotations. Unlike most previous studies, these rotation-invariant convolutions (RIConvs) have the same number of learnable parameters and a similar computational process as conventional convolution operations, allowing them to be interchangeable. Using the MNIST-Rot dataset, we first verify the invariance of these RIConvs under various rotation angles and compare their performance with previous rotation-invariant convolutional neural networks (RI-CNNs). Two types of RIConvs based on gradient operators achieve state-of-the-art results. Subsequently, we combine RIConvs with different types and depths of classic CNN backbones. Using the OuTex_00012, MTARSI, and NWPU-RESISC-45 datasets, we test their performance on texture recognition, aircraft type recognition, and remote sensing image classification tasks. The results show that RIConvs significantly improve the accuracy of these CNN backbones, especially when the training data is limited. Furthermore, we find that even with data augmentation, RIConvs can further enhance model performance.
Abstract (translated)
在不依赖数据的情况下实现深度神经网络的旋转不变性一直是一个热门的研究课题。固有旋转不变性可以增强模型的特征表示能力，从而在诸如多方向物体识别和检测等任务中取得更好的性能。根据各种非学习操作类型，包括梯度、排序、局部二值模式、最大等，本文设计了一组新的卷积操作，它们自然对任意旋转对称。与大多数之前的研究不同，这些旋转不变的卷积操作（RIConvs）具有与传统卷积操作相同的学习参数和类似的计算过程，因此可以互换。使用MNIST-Rot数据集，我们首先验证这些RIConvs在各种旋转角度下的不变性，并将其性能与之前的目标不变卷积神经网络（RI-CNNs）进行比较。基于梯度操作的两种RIConvs达到了最先进的结果。接着，我们将RIConvs与不同类型和深度的经典卷积网络骨干相结合。使用OuTex_00012、MTARSI和NWPU-RESISC-45数据集，我们测试了它们在纹理识别、飞机类型识别和遥感图像分类任务上的性能。结果表明，RIConvs显著提高了这些卷积网络骨干的准确性，特别是在训练数据有限的情况下。此外，我们发现，即使进行数据增强，RIConvs也可以进一步提高模型性能。
URL
https://arxiv.org/abs/2404.11309
