FILTRA: Rethinking Steerable CNN by Filter Transform
- URL: http://arxiv.org/abs/2105.11636v1
- Date: Tue, 25 May 2021 03:32:34 GMT
- Title: FILTRA: Rethinking Steerable CNN by Filter Transform
- Authors: Bo Li, Qili Wang, Gim Hee Lee
- Abstract summary: The problem of steerable CNN has been studied from aspect of group representation theory.
We show that kernel constructed by filter transform can also be interpreted in the group representation theory.
This interpretation help complete the puzzle of steerable CNN theory and provides a novel and simple approach to implement steerable convolution operators.
- Score: 59.412570807426135
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Steerable CNN imposes the prior knowledge of transformation invariance or
equivariance in the network architecture to enhance the the network robustness
on geometry transformation of data and reduce overfitting. It has been an
intuitive and widely used technique to construct a steerable filter by
augmenting a filter with its transformed copies in the past decades, which is
named as filter transform in this paper. Recently, the problem of steerable CNN
has been studied from aspect of group representation theory, which reveals the
function space structure of a steerable kernel function. However, it is not yet
clear on how this theory is related to the filter transform technique. In this
paper, we show that kernel constructed by filter transform can also be
interpreted in the group representation theory. This interpretation help
complete the puzzle of steerable CNN theory and provides a novel and simple
approach to implement steerable convolution operators. Experiments are executed
on multiple datasets to verify the feasibility of the proposed approach.
Related papers
- Rotation-Scale Equivariant Steerable Filters [1.213915839836187]
Digital histology imaging of biopsy tissue can be captured at arbitrary orientation and magnification and stored at different resolutions.
We propose the Rotation-Scale Equivariant Steerable Filter (RSESF), which incorporates steerable filters and scale-space theory.
Our method outperforms other approaches, with much fewer trainable parameters and fewer GPU resources required.
arXiv Detail & Related papers (2023-04-10T14:13:56Z) - A Continuous Convolutional Trainable Filter for Modelling Unstructured
Data [0.0]
We propose a continuous version of a trainable convolutional filter able to work also with unstructured data.
Our experiments show that the continuous filter can achieve a level of accuracy comparable to the state-of-the-art discrete filter.
arXiv Detail & Related papers (2022-10-24T17:34:10Z) - Understanding the Covariance Structure of Convolutional Filters [86.0964031294896]
Recent ViT-inspired convolutional networks such as ConvMixer and ConvNeXt use large-kernel depthwise convolutions with notable structure.
We first observe that such learned filters have highly-structured covariance matrices, and we find that covariances calculated from small networks may be used to effectively initialize a variety of larger networks.
arXiv Detail & Related papers (2022-10-07T15:59:13Z) - Batch Normalization Tells You Which Filter is Important [49.903610684578716]
We propose a simple yet effective filter pruning method by evaluating the importance of each filter based on the BN parameters of pre-trained CNNs.
The experimental results on CIFAR-10 and ImageNet demonstrate that the proposed method can achieve outstanding performance.
arXiv Detail & Related papers (2021-12-02T12:04:59Z) - Implicit Equivariance in Convolutional Networks [1.911678487931003]
Implicitly Equivariant Networks (IEN) induce equivariant in the different layers of a standard CNN model.
We show IEN outperforms the state-of-the-art rotation equivariant tracking method while providing faster inference speed.
arXiv Detail & Related papers (2021-11-28T14:44:17Z) - Graph Neural Networks with Adaptive Frequency Response Filter [55.626174910206046]
We develop a graph neural network framework AdaGNN with a well-smooth adaptive frequency response filter.
We empirically validate the effectiveness of the proposed framework on various benchmark datasets.
arXiv Detail & Related papers (2021-04-26T19:31:21Z) - DeConFuse : A Deep Convolutional Transform based Unsupervised Fusion
Framework [29.58965424136611]
This work proposes an unsupervised fusion framework based on deep convolutional transform learning.
We apply the proposed technique, named DeConFuse, on the problem of stock forecasting and trading.
arXiv Detail & Related papers (2020-11-09T11:04:09Z) - Filter Grafting for Deep Neural Networks: Reason, Method, and
Cultivation [86.91324735966766]
Filter is the key component in modern convolutional neural networks (CNNs)
In this paper, we introduce filter grafting (textbfMethod) to achieve this goal.
We develop a novel criterion to measure the information of filters and an adaptive weighting strategy to balance the grafted information among networks.
arXiv Detail & Related papers (2020-04-26T08:36:26Z) - Dense Steerable Filter CNNs for Exploiting Rotational Symmetry in
Histology Images [3.053417311299492]
Histology images are inherently symmetric under rotation, where each orientation is equally as likely to appear.
Dense Steerable Filter CNNs (DSF-CNNs) use group convolutions with multiple rotated copies of each filter in a densely connected framework.
We show that DSF-CNNs achieve state-of-the-art performance, with significantly fewer parameters, when applied to three different tasks in the area of pathology computational.
arXiv Detail & Related papers (2020-04-06T23:12:31Z) - Computational optimization of convolutional neural networks using
separated filters architecture [69.73393478582027]
We consider a convolutional neural network transformation that reduces computation complexity and thus speedups neural network processing.
Use of convolutional neural networks (CNN) is the standard approach to image recognition despite the fact they can be too computationally demanding.
arXiv Detail & Related papers (2020-02-18T17:42:13Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.