Rotation-Invariant Feature Learning via Convolutional Neural Network With Cyclic Polar Coordinates Convolutional Layer

Mei, Shaohui; Jiang, Ruoqiao; Ma, Mingyang; Song, Chao

doi:10.1109/tgrs.2022.3233726

Cited by 44 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The integration of DNNs into safety-critical applications, such as autonomous driving [55], [56], face recognition [57], [58], RS [1], [59], etc., highlights the criticality of enhancing model robustness and developing resilient DL systems. As a result, there is a growing need to comprehensively evaluate the robustness of DL models for a better understanding of the factors affecting their resilience and facilitate further improvements in DNNs' robustness.…”

Section: Surveymentioning

confidence: 99%

See 1 more Smart Citation

Benchmarking Adversarial Patch Against Aerial Detection

Lian

Mei

Zhang

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Deep neural networks (DNNs) have found widespread applications in interpreting remote sensing (RS) imagery. However, it has been demonstrated in previous works that DNNs are vulnerable to different types of noises, particularly adversarial noises. Surprisingly, there has been a lack of comprehensive studies on the robustness of RS tasks, prompting us to undertake a thorough survey and benchmark on the robustness of image classification and object detection in RS. To our best knowledge, this study represents the first comprehensive examination of both natural robustness and adversarial robustness in RS tasks. Specifically, we have curated and made publicly available datasets that contain natural and adversarial noises. These datasets serve as valuable resources for evaluating the robustness of DNNs-based models. To provide a comprehensive assessment of model robustness, we conducted meticulous experiments with numerous different classifiers and detectors, encompassing a wide range of mainstream methods. Through rigorous evaluation, we have uncovered insightful and intriguing findings, which shed light on the relationship between adversarial noise crafting and model training, yielding a deeper understanding of the susceptibility and limitations of various models, and providing guidance for the development of more resilient and robust models

show abstract

Section: Surveymentioning

confidence: 99%

“…Lap-Pui Chau is with the Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong, China (lappui.chau@polyu.edu.hk). RSIs, there has been a surge in the development of diverse techniques for aerial detection [1]- [4] over the past few years.…”

Section: Introductionmentioning

confidence: 99%

Benchmarking Adversarial Patch Against Aerial Detection

Lian

Mei

Zhang

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Therefore, HSIs have been successfully applied to various fields due to their high development potential and application value, including agriculture [2], pathological detection [3], the military [4], environmental governance [5] and so on. In addition, hyperspectral imaging technology further promotes the development of computer vision to a great extent, such as target detection [6], target tracking [7,8], target classification [9,10] and other high-level tasks [11][12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

Tensor-Based Sparse Representation for Hyperspectral Image Reconstruction Using RGB Inputs

Duan,

Wang,

Zhang

et al. 2024

Mathematics

View full text Add to dashboard Cite

Hyperspectral image (HSI) reconstruction from RGB input has drawn much attention recently and plays a crucial role in further vision tasks. However, current sparse coding algorithms often take each single pixel as the basic processing unit during the reconstruction process, which ignores the strong similarity and relation between adjacent pixels within an image or scene, leading to an inadequate learning of spectral and spatial features in the target hyperspectral domain. In this paper, a novel tensor-based sparse coding method is proposed to integrate both spectral and spatial information represented in tensor forms, which is capable of taking all the neighboring pixels into account during the spectral super-resolution (SSR) process without breaking the semantic structures, thus improving the accuracy of the final results. Specifically, the proposed method recovers the unknown HSI signals using sparse coding on the learned dictionary pairs. Firstly, the spatial information of pixels is used to constrain the sparse reconstruction process, which effectively improves the spectral reconstruction accuracy of pixels. In addition, the traditional two-dimensional dictionary learning is further extended to the tensor domain, by which the structure of inputs can be processed in a more flexible way, thus enhancing the spatial contextual relations. To this end, a rudimentary HSI estimation acquired in the sparse reconstruction stage is further enhanced by introducing the regression method, aiming to eliminate the spectral distortion to some extent. Abundant experiments are conducted on two public datasets, indicating the considerable availability of the proposed framework.

show abstract

“…These models include Spatial Transformer Network (STN) [14], Polar Transformer Network [15], Oriented Response Network (ORN) [16], Rotation-Invariant Coordinate CNN (RIC-CNN) [17], and so on [18], [19], [20], [21]. Although they have been used in different practical tasks [22], [23], [24], [25], [26], [27], these existing rotation-invariant/equivariant CNNs have three major limitations: 1) Most methods are invariant to specific rotation angles rather than arbitrary angles [9], [16], [20]. Some of them, like RIC-CNN [17], are only invariant to rotations around image center.…”

Section: Introductionmentioning

confidence: 99%

Sorting Convolution Operation for Achieving Rotational Invariance

Mo,

Zhao

2024

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

The topic of achieving rotational invariance in convolutional neural networks (CNNs) has gained considerable attention recently, as this invariance is crucial for many computer vision tasks. In this letter, we propose a sorting convolution operation (SConv), which achieves invariance to arbitrary rotations without additional learnable parameters or data augmentation. It can directly replace conventional convolution operations in a classic CNN model to achieve the model's rotational invariance. Based on MNIST-rot dataset, we first analyze the impact of convolution kernel size, sampling grid and sorting method on SConv's rotational invariance, and compare our method with previous rotation-invariant CNN models. Then, we combine SConv with VGG, ResNet and DenseNet, and conduct classification experiments on texture and remote sensing image datasets. The results show that SConv significantly improves the performance of these models, especially when training data is limited. Our code can be downloaded from https://github.com/HanlinMo/Sorting-Convolution-Operation-for-Achieving-Rotational-Invariance.

show abstract

Rotation-Invariant Feature Learning via Convolutional Neural Network With Cyclic Polar Coordinates Convolutional Layer

Cited by 44 publications

References 30 publications

Benchmarking Adversarial Patch Against Aerial Detection

Benchmarking Adversarial Patch Against Aerial Detection

Tensor-Based Sparse Representation for Hyperspectral Image Reconstruction Using RGB Inputs

Sorting Convolution Operation for Achieving Rotational Invariance

Contact Info

Product

Resources

About