首页/论文/2210.08001

arXiv 2210.080012022-10-14cs.CVcs.AIcs.LG

Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks

University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Purdue University（普渡大学）

Renan A. Rojas-Gomez, Teck-Yian Lim, Alexander G. Schwing, Minh N. Do, Raymond A. Yeh

备注：: Accepted at the Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

We propose learnable polyphase sampling (LPS), a pair of learnable down/upsampling layers that enable truly shift-invariant and equivariant convolutional networks. LPS can be trained end-to-end from data and generalizes existing handcrafted downsampling layers. It is widely applicable as it can be integrated into any convolutional network by replacing down/upsampling layers. We evaluate LPS on image classification and semantic segmentation. Experiments show that LPS is on-par with or outperforms existing methods in both performance and shift consistency. For the first time, we achieve true shift-equivariance on semantic segmentation (PASCAL VOC), i.e., 100% shift consistency, outperforming baselines by an absolute 3.3%.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

利用平移不变多相采样提升卷积神经网络的移位不变性

Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase Sampling

University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）

针对下采样破坏 CNN 移位不变性的问题，提出可学习的 TIPS 池化及两种正则化以降低 MSB，在分类、分割及鲁棒性基准上实现一致提升。

2024-12-01cs.CVcs.LG

移位等价复值卷积神经网络

Shift-Equivariant Complex-Valued Convolutional Neural Networks

SONDRA, CentraleSupélec, Université Paris-Saclay（SONDRA、CentraleSupélec、巴黎-萨克雷大学）；LORIA, CNRS, CentraleSupélec, Université Paris-Saclay（LORIA、CNRS、CentraleSupélec、巴黎-萨克雷大学）；DEMR, ONERA, Université Paris-Saclay（DEMR、ONERA、巴黎-萨克雷大学）；DSO National Laboratories（DSO国家实验室）

本文提出复值神经网络中的移位等价性方法，通过引入投影层和可学习多相上/下采样技术，提升计算机视觉任务中的不变性和等价性性能。

2025-11-26cs.CV

Truly shift-equivariant convolutional neural networks with adaptive polyphase upsampling

University of Basel（巴塞尔大学）

Convolutional neural networks lack shift equivariance due to the presence of downsampling layers. In image classification, adaptive polyphase downsampling (APS-D) was recently proposed to make CNNs perfectly shift invariant. However, in networks used for image reconstruction tasks, it can not by itself restore shift equivariance. We address this problem by proposing adaptive polyphase upsampling (APS-U), a non-linear extension of conventional upsampling, which allows CNNs with symmetric encoder-decoder architecture (for example U-Net) to exhibit perfect shift equivariance. With MRI and CT reco…

2021-12-06cs.CVeess.SP

视觉中通过$G$-Biases实现松弛旋转等变性

Relaxed Rotational Equivariance via $G$-Biases in Vision

Software Engineering Institute, East China Normal University（华东师范大学软件工程研究所）；School of Geospatial Information, Information Engineering University（信息工程大学地理空间信息学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；School of Communication and Electronic Engineering, East China Normal University（华东师范大学通信与电子工程学院）；Institute of Machine Intelligence, University of Shanghai for Science and Technology（上海理工大学机器智能研究院）；School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）

针对真实数据存在旋转对称性破缺导致群等变卷积适配性差的问题，提出基于可学习$G$-Biases的松弛旋转等变卷积RREConv，在分类和2D目标检测任务上性能优于现有GConv方法。

2025-01-14cs.AIcs.CV

RRL:Regional Rotation Layer in Convolutional Neural Networks

University of Electronic Science and Technology of China（电子科技大学）

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 fe…

2022-02-25cs.CV

PE-CSNet：一种具有可学习基于块的稀疏表示的等变网络架构

PE-CSNet: An equivariant network architecture with learnable patch-based sparse representation

The Hong Kong Polytechnic University（香港理工大学）；Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；University of Chinese Academy of Sciences（中国科学院大学）

针对压缩感知中稀疏变换与优化设计的难题，提出PE-CSNet等变深度展开架构，结合可学习稀疏性与随机等变训练，在CS-MRI等任务上性能优于传统及现有深度展开方法

2026-08-18cs.CV

更多相关论文收起更多论文

Rescaling CNN through Learnable Repetition of Network Parameters

Transmute AI Lab, Texmin Hub, IIT Dhanbad（IIT Dhanbad（印度理工学院丹巴德分校）Transmute AI Lab，Texmin Hub）

Deeper and wider CNNs are known to provide improved performance for deep learning tasks. However, most such networks have poor performance gain per parameter increase. In this paper, we investigate whether the gain observed in deeper models is purely due to the addition of more optimization parameters or whether the physical size of the network as well plays a role. Further, we present a novel rescaling strategy for CNNs based on learnable repetition of its parameters. Based on this strategy, we rescale CNNs without changing their parameter count, and show that learnable sharing of weights its…

2021-08-19cs.CV

具有旋转对称先验的图像到图像翻译框架

Image-to-Image Translation Framework Embedded with Rotation Symmetry Priors

School of Mathematics and Statistics, Xi’an Jiaotong University, Shaanxi, P.R.China（西安交通大学数学与统计学学院，陕西省，中华人民共和国）

本文提出基于旋转对称先验的图像到图像翻译框架，通过引入旋转群等价卷积实现旋转等价翻译网络，理论分析TL-Conv的等价误差，并在多种I2I任务中验证其有效性。

2026-04-14cs.CV

TetraSphere：一种用于O(3)不变点云分析的神经描述符

TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis

Computer Vision Laboratory, Department of Electrical Engineering, Linköping University（林雪平大学电气工程系计算机视觉实验室）

本文提出TetraSphere，一种基于可旋转3D球神经元和向量神经元的O(3)不变描述符，通过端到端训练提升点云旋转不变性，在ScanObjectNN和ModelNet40上取得新突破。

2024-03-25cs.CV

对齐网络等价性与数据对称性：图像恢复的理论框架和自适应方法

Aligning Network Equivariance with Data Symmetry: A Theoretical Framework and Adaptive Approach for Image Restoration

School of Mathematics and Statistics（数学与统计学学院）

本文提出理论框架和自适应方法，通过量化数据对称性约束优化图像恢复的偏差方差权衡，验证了等价性与数据对称性的内在关系。

2026-05-13cs.CV