Achieving Rotation Invariance in Convolution Operations: Shifting from Data-Driven to Mechanism-Assured
- URL: http://arxiv.org/abs/2404.11309v1
- Date: Wed, 17 Apr 2024 12:21:57 GMT
- Title: Achieving Rotation Invariance in Convolution Operations: Shifting from Data-Driven to Mechanism-Assured
- Authors: Hanlin Mo, Guoying Zhao,
- Abstract summary: This paper designs a set of new convolution operations that are natually invariant to arbitrary rotations.
We compare their performance with previous rotation-invariant convolutional neural networks (RI-CNNs)
The results show that RIConvs significantly improve the accuracy of these CNN backbones, especially when the training data is limited.
- Score: 18.910817148765176
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- 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.
Related papers
- Revisiting Data Augmentation for Rotational Invariance in Convolutional
Neural Networks [0.29127054707887967]
We investigate how best to include rotational invariance in a CNN for image classification.
Our experiments show that networks trained with data augmentation alone can classify rotated images nearly as well as in the normal unrotated case.
arXiv Detail & Related papers (2023-10-12T15:53:24Z) - FRS-Nets: Fourier Parameterized Rotation and Scale Equivariant Networks
for Retinal Vessel Segmentation [55.4653338610275]
We construct a novel convolution operator (FRS-Conv), which is Fourier parameterized and equivariant to rotation and scaling.
With merely 13.9% parameters of corresponding baselines, FRS-Nets have achieved state-of-the-art performance.
It demonstrates the remarkable accuracy, generalization, and clinical application potential of FRS-Nets.
arXiv Detail & Related papers (2023-09-27T13:14:57Z) - Sorted Convolutional Network for Achieving Continuous Rotational
Invariance [56.42518353373004]
We propose a Sorting Convolution (SC) inspired by some hand-crafted features of texture images.
SC achieves continuous rotational invariance without requiring additional learnable parameters or data augmentation.
Our results demonstrate that SC achieves the best performance in the aforementioned tasks.
arXiv Detail & Related papers (2023-05-23T18:37:07Z) - RIC-CNN: Rotation-Invariant Coordinate Convolutional Neural Network [56.42518353373004]
We propose a new convolutional operation, called Rotation-Invariant Coordinate Convolution (RIC-C)
By replacing all standard convolutional layers in a CNN with the corresponding RIC-C, a RIC-CNN can be derived.
It can be observed that RIC-CNN achieves the state-of-the-art classification on the rotated test dataset of MNIST.
arXiv Detail & Related papers (2022-11-21T19:27:02Z) - ReF -- Rotation Equivariant Features for Local Feature Matching [30.459559206664427]
We propose an alternative, complementary approach that centers on inducing bias in the model architecture itself to generate rotation-specific' features.
We demonstrate that this high performance, rotation-specific coverage from the steerable CNNs can be expanded to all rotation angles.
We present a detailed analysis of the performance effects of ensembling, robust estimation, network architecture variations, and the use of rotation priors.
arXiv Detail & Related papers (2022-03-10T07:36:09Z) - Improving the Sample-Complexity of Deep Classification Networks with
Invariant Integration [77.99182201815763]
Leveraging prior knowledge on intraclass variance due to transformations is a powerful method to improve the sample complexity of deep neural networks.
We propose a novel monomial selection algorithm based on pruning methods to allow an application to more complex problems.
We demonstrate the improved sample complexity on the Rotated-MNIST, SVHN and CIFAR-10 datasets.
arXiv Detail & Related papers (2022-02-08T16:16:11Z) - OneDConv: Generalized Convolution For Transform-Invariant Representation [76.15687106423859]
We propose a novel generalized one dimension convolutional operator (OneDConv)
It dynamically transforms the convolution kernels based on the input features in a computationally and parametrically efficient manner.
It improves the robustness and generalization of convolution without sacrificing the performance on common images.
arXiv Detail & Related papers (2022-01-15T07:44:44Z) - GhostSR: Learning Ghost Features for Efficient Image Super-Resolution [49.393251361038025]
Single image super-resolution (SISR) system based on convolutional neural networks (CNNs) achieves fancy performance while requires huge computational costs.
We propose to use shift operation to generate the redundant features (i.e., Ghost features) of SISR models.
We show that both the non-compact and lightweight SISR models embedded in our proposed module can achieve comparable performance to that of their baselines.
arXiv Detail & Related papers (2021-01-21T10:09:47Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.