中文
相关论文

相关论文: Inability of spatial transformations of CNN featur…

200 篇论文

Spatial transformer networks (STNs) were designed to enable convolutional neural networks (CNNs) to learn invariance to image transformations. STNs were originally proposed to transform CNN feature maps as well as input images. This enables…

计算机视觉与模式识别 · 计算机科学 2024-09-19 Lukas Finnveden , Ylva Jansson , Tony Lindeberg

Spatial transformer networks (STNs) were designed to enable CNNs to learn invariance to image transformations. STNs were originally proposed to transform CNN feature maps as well as input images. This enables the use of more complex…

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

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with…

计算机视觉与模式识别 · 计算机科学 2019-12-04 Xu Shen , Xinmei Tian , Anfeng He , Shaoyan Sun , Dacheng Tao

Convolutional Neural Networks (CNNs) are commonly assumed to be invariant to small image transformations: either because of the convolutional architecture or because they were trained using data augmentation. Recently, several authors have…

计算机视觉与模式识别 · 计算机科学 2020-01-24 Aharon Azulay , Yair Weiss

In this paper we challenge the common assumption that convolutional layers in modern CNNs are translation invariant. We show that CNNs can and will exploit the absolute spatial location by learning filters that respond exclusively to…

计算机视觉与模式识别 · 计算机科学 2020-06-02 Osman Semih Kayhan , Jan C. van Gemert

Convolutional Neural Networks (CNNs) require large image corpora to be trained on classification tasks. The variation in image resolutions, sizes of objects and patterns depicted, and image scales, hampers CNN training and performance,…

计算机视觉与模式识别 · 计算机科学 2016-05-16 Nanne van Noord , Eric Postma

Convolutional Neural Networks (CNNs) define an exceptionally powerful class of models for image classification, but the theoretical background and the understanding of how invariances to certain transformations are learned is limited. In a…

计算机视觉与模式识别 · 计算机科学 2018-03-19 Charlotte Bunne , Lukas Rahmann , Thomas Wolf

Convolutional Neural Networks (CNNs) are extremely efficient, since they exploit the inherent translation-invariance of natural images. However, translation is just one of a myriad of useful spatial transformations. Can the same efficiency…

计算机视觉与模式识别 · 计算机科学 2021-12-02 João F. Henriques , Andrea Vedaldi

This paper is concerned with a fundamental problem in geometric deep learning that arises in the construction of convolutional neural networks on surfaces. Due to curvature, the transport of filter kernels on surfaces results in a…

计算机视觉与模式识别 · 计算机科学 2020-06-03 Ruben Wiersma , Elmar Eisemann , Klaus Hildebrandt

Convolutional Neural Networks (CNN) offer state of the art performance in various computer vision tasks. Many of those tasks require different subtypes of affine invariances (scale, rotational, translational) to image transformations.…

计算机视觉与模式识别 · 计算机科学 2023-10-13 Facundo Manuel Quiroga , Franco Ronchetti , Laura Lanzarini , Aurelio Fernandez-Bariviera

Omnidirectional images and spherical representations of $3D$ shapes cannot be processed with conventional 2D convolutional neural networks (CNNs) as the unwrapping leads to large distortion. Using fast implementations of spherical and…

计算机视觉与模式识别 · 计算机科学 2020-12-09 Suhas Lohit , Shubhendu Trivedi

Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map…

计算机视觉与模式识别 · 计算机科学 2017-04-12 Daniel E. Worrall , Stephan J. Garbin , Daniyar Turmukhambetov , Gabriel J. Brostow

When seeing a new object, humans can immediately recognize it across different retinal locations: we say that the internal object representation is invariant to translation. It is commonly believed that Convolutional Neural Networks (CNNs)…

计算机视觉与模式识别 · 计算机科学 2020-11-25 Valerio Biscione , Jeffrey Bowers

Convolutional Neural Networks define an exceptionally powerful class of models, but are still limited by the lack of ability to be spatially invariant to the input data in a computationally and parameter efficient manner. In this work we…

计算机视觉与模式识别 · 计算机科学 2016-02-05 Max Jaderberg , Karen Simonyan , Andrew Zisserman , Koray Kavukcuoglu

We present a method for learning discriminative filters using a shallow Convolutional Neural Network (CNN). We encode rotation invariance directly in the model by tying the weights of groups of filters to several rotated versions of the…

计算机视觉与模式识别 · 计算机科学 2017-05-03 Diego Marcos , Michele Volpi , Devis Tuia

When seeing a new object, humans can immediately recognize it across different retinal locations: the internal object representation is invariant to translation. It is commonly believed that Convolutional Neural Networks (CNNs) are…

计算机视觉与模式识别 · 计算机科学 2021-10-13 Valerio Biscione , Jeffrey S. Bowers

Convolutional Neural Networks (CNN) has been widely applied in the realm of computer vision. However, given the fact that CNN models are translation invariant, they are not aware of the coordinate information of each pixel. Thus the…

计算机视觉与模式识别 · 计算机科学 2020-03-25 Liliang Ren , Zhuonan Hao

In this work we investigate how to achieve equivariance to input transformations in deep networks, purely from data, without being given a model of those transformations. Convolutional Neural Networks (CNNs), for example, are equivariant to…

计算机视觉与模式识别 · 计算机科学 2021-11-29 Jianbo Jiao , João F. Henriques

Deep Convolutional Neural Networks (CNNs) are empirically known to be invariant to moderate translation but not to rotation in image classification. This paper proposes a deep CNN model, called CyCNN, which exploits polar mapping of input…

计算机视觉与模式识别 · 计算机科学 2020-07-23 Jinpyo Kim , Wooekun Jung , Hyungmo Kim , Jaejin Lee

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…

计算机视觉与模式识别 · 计算机科学 2017-07-26 Zhun Sun , Mete Ozay , Takayuki Okatani
‹ 上一页 1 2 3 10 下一页 ›