中文
相关论文

相关论文: Riesz networks: scale invariant neural networks in…

200 篇论文

Scattering networks yield powerful and robust hierarchical image descriptors which do not require lengthy training and which work well with very few training data. However, they rely on sampling the scale dimension. Hence, they become…

计算机视觉与模式识别 · 计算机科学 2024-01-12 Tin Barisin , Jesus Angulo , Katja Schladitz , Claudia Redenbach

The ability to handle large scale variations is crucial for many real world visual tasks. A straightforward approach for handling scale in a deep network is to process an image at several scales simultaneously in a set of scale channels.…

计算机视觉与模式识别 · 计算机科学 2022-04-13 Ylva Jansson , Tony Lindeberg

The widespread success of convolutional neural networks may largely be attributed to their intrinsic property of translation equivariance. However, convolutions are not equivariant to variations in scale and fail to generalize to objects of…

计算机视觉与模式识别 · 计算机科学 2022-11-21 Thomas Altstidl , An Nguyen , Leo Schwinn , Franz Köferl , Christopher Mutschler , Björn Eskofier , Dario Zanca

The effectiveness of Convolutional Neural Networks (CNNs) has been substantially attributed to their built-in property of translation equivariance. However, CNNs do not have embedded mechanisms to handle other types of transformations. In…

计算机视觉与模式识别 · 计算机科学 2020-02-07 Ivan Sosnovik , Michał Szmaja , Arnold Smeulders

Even though convolutional neural networks (CNN) has achieved near-human performance in various computer vision tasks, its ability to tolerate scale variations is limited. The popular practise is making the model bigger first, and then train…

计算机视觉与模式识别 · 计算机科学 2014-11-25 Yichong Xu , Tianjun Xiao , Jiaxing Zhang , Kuiyuan Yang , Zheng Zhang

An important capacity in visual object recognition is invariance to image-altering variables which leave the identity of objects unchanged, such as lighting, rotation, and scale. How do neural networks achieve this? Prior mechanistic…

计算机视觉与模式识别 · 计算机科学 2025-05-01 André Longon

Convolutional Neural Networks (ConvNets) have shown excellent results on many visual classification tasks. With the exception of ImageNet, these datasets are carefully crafted such that objects are well-aligned at similar scales. Naturally,…

计算机视觉与模式识别 · 计算机科学 2014-12-17 Angjoo Kanazawa , Abhishek Sharma , David Jacobs

While scale-invariant modeling has substantially boosted the performance of visual recognition tasks, it remains largely under-explored in deep networks based image restoration. Naively applying those scale-invariant techniques (e.g.…

计算机视觉与模式识别 · 计算机科学 2019-12-20 Yuchen Fan , Jiahui Yu , Ding Liu , Thomas S. Huang

The ability to handle large scale variations is crucial for many real world visual tasks. A straightforward approach for handling scale in a deep network is to process an image at several scales simultaneously in a set of scale channels.…

计算机视觉与模式识别 · 计算机科学 2024-09-20 Ylva Jansson , Tony Lindeberg

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…

计算机视觉与模式识别 · 计算机科学 2022-03-11 Sam Buchanan , Jingkai Yan , Ellie Haber , John Wright

We introduce deep scale-spaces (DSS), a generalization of convolutional neural networks, exploiting the scale symmetry structure of conventional image recognition tasks. Put plainly, the class of an image is invariant to the scale at which…

机器学习 · 计算机科学 2019-05-29 Daniel E. Worrall , Max Welling

Scale invariance profoundly influences the dynamics and structure of complex systems, spanning from critical phenomena to network architecture. Here, we propose a precise definition of scale-invariant networks by leveraging the concept of a…

统计力学 · 物理学 2024-12-17 Anna Poggialini , Pablo Villegas , Miguel A. Muñoz , Andrea Gabrielli

The ability of convolutional neural networks (CNNs) to recognize objects regardless of their position in the image is due to the translation-equivariance of the convolutional operation. Group-equivariant CNNs transfer this equivariance to…

计算机视觉与模式识别 · 计算机科学 2023-04-13 Thomas Wimmer , Vladimir Golkov , Hoai Nam Dang , Moritz Zaiss , Andreas Maier , Daniel Cremers

This paper presents a hybrid approach between scale-space theory and deep learning, where a deep learning architecture is constructed by coupling parameterized scale-space operations in cascade. By sharing the learnt parameters between…

计算机视觉与模式识别 · 计算机科学 2024-09-19 Tony Lindeberg

Systems with lattice geometry can be renormalized exploiting their coordinates in metric space, which naturally define the coarse-grained nodes. By contrast, complex networks defy the usual techniques, due to their small-world character and…

物理与社会 · 物理学 2023-11-07 Elena Garuccio , Margherita Lalli , Diego Garlaschelli

Generalisation across image scales remains a fundamental challenge for deep networks, which often fail to handle images at scales not seen during training (the out-of-distribution problem). In this paper, we present provably scale-invariant…

计算机视觉与模式识别 · 计算机科学 2026-03-04 Andrzej Perzanowski , Tony Lindeberg

Just like weights, bias terms are the learnable parameters of many popular machine learning models, including neural networks. Biases are thought to enhance the representational power of neural networks, enabling them to solve a variety of…

计算机视觉与模式识别 · 计算机科学 2023-05-30 Chuqin Geng , Xiaojie Xu , Haolin Ye , Xujie Si

Conventional scaling of neural networks typically involves designing a base network and growing different dimensions like width, depth, etc. of the same by some predefined scaling factors. We introduce an automated scaling approach…

机器学习 · 计算机科学 2024-02-21 Akash Guna R. T , Arnav Chavan , Deepak Gupta

Convolutional Neural Network(CNN) has been widely used for image recognition with great success. However, there are a number of limitations of the current CNN based image recognition paradigm. First, the receptive field of CNN is generally…

计算机视觉与模式识别 · 计算机科学 2018-03-28 Dong-Qing Zhang

Learned inverse problem solvers exhibit remarkable performance in applications like image reconstruction tasks. These data-driven reconstruction methods often follow a two-step scheme. First, one trains the often neural network-based…

‹ 上一页 1 2 3 10 下一页 ›