English
Related papers

Related papers: Achieving Rotation Invariance in Convolution Opera…

200 papers

In this work, we address the problem of improvement of robustness of feature representations learned using convolutional neural networks (CNNs) to image deformation. We argue that higher moment statistics of feature distributions could be…

Computer Vision and Pattern Recognition · Computer Science 2017-07-26 Zhun Sun , Mete Ozay , Takayuki Okatani

This work attempts to interpret modern deep (convolutional) networks from the principles of rate reduction and (shift) invariant classification. We show that the basic iterative gradient ascent scheme for optimizing the rate reduction of…

Machine Learning · Computer Science 2020-10-30 Kwan Ho Ryan Chan , Yaodong Yu , Chong You , Haozhi Qi , John Wright , Yi Ma

We propose Re-parameterized Refocusing Convolution (RefConv) as a replacement for regular convolutional layers, which is a plug-and-play module to improve the performance without any inference costs. Specifically, given a pre-trained model,…

Computer Vision and Pattern Recognition · Computer Science 2023-10-17 Zhicheng Cai , Xiaohan Ding , Qiu Shen , Xun Cao

Recently, many deep neural networks were designed to process 3D point clouds, but a common drawback is that rotation invariance is not ensured, leading to poor generalization to arbitrary orientations. In this paper, we introduce a new…

Computer Vision and Pattern Recognition · Computer Science 2021-07-06 Xianzhi Li , Ruihui Li , Guangyong Chen , Chi-Wing Fu , Daniel Cohen-Or , Pheng-Ann Heng

Rotation-invariant (RI) 3D deep learning methods suffer performance degradation as they typically design RI representations as input that lose critical global information comparing to 3D coordinates. Most state-of-the-arts address it by…

Computer Vision and Pattern Recognition · Computer Science 2022-05-31 Ronghan Chen , Yang Cong

This paper presents a novel approach to exploit the distinctive invariant features in convolutional neural network. The proposed CNN model uses Scale Invariant Feature Transform (SIFT) descriptor instead of the max-pooling layer.…

Computer Vision and Pattern Recognition · Computer Science 2019-04-02 Abhay Kumar , Nishant Jain , Chirag Singh , Suraj Tripathi

Processing of missing data by modern neural networks, such as CNNs, remains a fundamental, yet unsolved challenge, which naturally arises in many practical applications, like image inpainting or autonomous vehicles and robots. While…

Machine Learning · Computer Science 2021-11-01 Marcin Przewięźlikowski , Marek Śmieja , Łukasz Struski , Jacek Tabor

Although convolutional networks (ConvNets) have enjoyed great success in computer vision (CV), it suffers from capturing global information crucial to dense prediction tasks such as object detection and segmentation. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2021-05-12 Haotian Yan , Zhe Li , Weijian Li , Changhu Wang , Ming Wu , Chuang Zhang

The success of building a high-resolution velocity model using machine learning is hampered by generalization limitations that often limit the success of the approach on field data. This is especially true when relying on neural operators…

Geophysics · Physics 2025-09-25 Xiao Ma , Tariq Alkhalifah

The intrinsic rotation invariance lies at the core of matching point clouds with handcrafted descriptors. However, it is widely despised by recent deep matchers that obtain the rotation invariance extrinsically via data augmentation. As the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Hao Yu , Zheng Qin , Ji Hou , Mahdi Saleh , Dongsheng Li , Benjamin Busam , Slobodan Ilic

Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains…

Computer Vision and Pattern Recognition · Computer Science 2021-12-10 Chengxi Ye , Xiong Zhou , Tristan McKinney , Yanfeng Liu , Qinggang Zhou , Fedor Zhdanov

Convolution is a central operation in Convolutional Neural Networks (CNNs), which applies a kernel to overlapping regions shifted across the image. However, because of the strong correlations in real-world image data, convolutional kernels…

Achieving invariance to nuisance transformations is a fundamental challenge in the construction of robust and reliable vision systems. Existing approaches to invariance scale exponentially with the dimension of the family of…

Computer Vision and Pattern Recognition · Computer Science 2022-03-11 Sam Buchanan , Jingkai Yan , Ellie Haber , John Wright

Deep convolutional neural networks (CNNs) have delivered superior performance in many computer vision tasks. In this paper, we propose a novel deep fully convolutional network model for accurate salient object detection. The key…

Computer Vision and Pattern Recognition · Computer Science 2017-08-08 Pingping Zhang , Dong Wang , Huchuan Lu , Hongyu Wang , Baocai Yin

Deep learning on point clouds has made a lot of progress recently. Many point cloud dedicated deep learning frameworks, such as PointNet and PointNet++, have shown advantages in accuracy and speed comparing to those using traditional 3D…

Computational Geometry · Computer Science 2018-12-18 Guanghua Pan , Jun Wang , Rendong Ying , Peilin Liu

Neural networks based on convolutional operations have achieved remarkable results in the field of deep learning, but there are two inherent flaws in standard convolutional operations. On the one hand, the convolution operation is confined…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Xin Zhang , Yingze Song , Tingting Song , Degang Yang , Yichen Ye , Jie Zhou , Liming Zhang

Handling geometric transformations, particularly rotations, remains a challenge in deep learning for computer vision. Standard neural networks lack inherent rotation invariance and typically rely on data augmentation or architectural…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Cristian Valero-Abundio , Emilio Sansano-Sansano , Raúl Montoliu , Marina Martínez García

We introduce a novel weighted convolution operator that enhances traditional convolutional neural networks (CNNs) by integrating a spatial density function into the convolution operator. This extension enables the network to differentially…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Simone Cammarasana , Giuseppe Patanè

We analyze the role of rotational equivariance in convolutional neural networks (CNNs) applied to spherical images. We compare the performance of the group equivariant networks known as S2CNNs and standard non-equivariant CNNs trained with…

Machine Learning · Computer Science 2022-07-13 Jan E. Gerken , Oscar Carlsson , Hampus Linander , Fredrik Ohlsson , Christoffer Petersson , Daniel Persson

Compared to the great progress of large-scale vision transformers (ViTs) in recent years, large-scale models based on convolutional neural networks (CNNs) are still in an early state. This work presents a new large-scale CNN-based…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 Wenhai Wang , Jifeng Dai , Zhe Chen , Zhenhang Huang , Zhiqi Li , Xizhou Zhu , Xiaowei Hu , Tong Lu , Lewei Lu , Hongsheng Li , Xiaogang Wang , Yu Qiao
‹ Prev 1 3 4 5 6 7 10 Next ›