Reducing Spatial Redundancy in CNN with Octave Convolution

Convolutional Neural Networks (CNNs) have achieved significant success in many computer vision tasks. In recent years, they have reduced DenseNet model parameters and feature map channel dimensions. In terms of the inherent redundancy of the number , its efficiency continues to improve. However, the feature maps generated by CNNs also have a lot of redundancy in the spatial dimension. Each location stores its own feature descriptor independently, ignoring the common information between adjacent locations that can be stored and processed together.

Natural images can be decomposed into low spatial frequency components that describe smoothly changing structures and high spatial frequency components that describe fast-changing fine details .

[1] believe that the output feature map of the convolutional layer can also be decomposed into features of different spatial frequencies, and propose a new multi-frequency feature representation method, which stores high-frequency and low-frequency feature maps into different group.

Therefore, through information sharing between adjacent locations, the spatial resolution of the low-frequency group can be safely reduced, and the spatial redundancy is reduced.

Jobs in AI

Octave Feature Representation

In order to reduce this spatial redundancy, [1] introduced the octave feature representation, which explicitly decomposes the feature map tensor into groups corresponding to low and high frequencies.

#cnn #convolutional-network #ai #image-processing #machine-learning

What is GEEK

Buddha Community

Reducing Spatial Redundancy in CNN with Octave Convolution

Convolutional Neural Networks (CNNs) have achieved significant success in many computer vision tasks. In recent years, they have reduced DenseNet model parameters and feature map channel dimensions. In terms of the inherent redundancy of the number , its efficiency continues to improve. However, the feature maps generated by CNNs also have a lot of redundancy in the spatial dimension. Each location stores its own feature descriptor independently, ignoring the common information between adjacent locations that can be stored and processed together.

Natural images can be decomposed into low spatial frequency components that describe smoothly changing structures and high spatial frequency components that describe fast-changing fine details .

[1] believe that the output feature map of the convolutional layer can also be decomposed into features of different spatial frequencies, and propose a new multi-frequency feature representation method, which stores high-frequency and low-frequency feature maps into different group.

Therefore, through information sharing between adjacent locations, the spatial resolution of the low-frequency group can be safely reduced, and the spatial redundancy is reduced.

Jobs in AI

Octave Feature Representation

In order to reduce this spatial redundancy, [1] introduced the octave feature representation, which explicitly decomposes the feature map tensor into groups corresponding to low and high frequencies.

#cnn #convolutional-network #ai #image-processing #machine-learning

CNN Series Part 1: How do computers see images?

In this article, we will learn about how computers see images & the issues faced while performing a computer vision task. We will see how deep learning comes into the picture & how with the power of neural networks, we can build a powerful computer vision system capable of solving extraordinary problems.

One example of how deep learning is transforming computer vision is facial recognition or face detection. On the top left, you can see the icon of the human eye which visually represents vision coming into the deep neural network in the form of images, pixels, videos & on the output on the bottom you can see a depiction of the human face or detection of the human face or this could also be recognizing different human faces or emotions on the face and also the key facial features, etc.

#convolution-neural-net #computer-vision #neural-networks #cnn #convolutional-network #series

How to Choose the Size of The Convolution Filter or Kernel Size for CNN?

Convolution is basically a dot product of kernel (or filter) and patch of an image (local receptive field) of the same size. Convolution is quite similar to correlation and exhibits a property of translation equivariant that means if we move or translate the input and apply the convolution to it, it will act in the same manner as we first apply convolution and then translated an image.

During this learning process of CNN, you find different kernel sizes at different places in the code, then this question arises in one’s mind that whether there is a specific way to choose such dimensions or sizes. So, the answer is no. In the current Deep Learning world, we are using the most popular choice that is used by every Deep Learning practitioner out there, and that is 3x3 kernel size. Now, another question strikes your mind, why only 3x3, and not 1x1, 2x2, 4x4, etc. Just keep reading and you will getthe most crisp reason behind this in next few minutes!!

#convolutional-network #data-science #neural-networks #cnn #deeplearing

CheatSheet: Convolutional Neural Network (CNN)

It is also termed as ConvNet that is a Deep learning algorithm that inputs an image, draws different feature maps using different kernels that allocates learnable weights to different objects in the image so as to differentiate from one another. The algorithm is widely used for various Image related tasks like classification, segmentation etc.

#cheat sheets #cnn #convolutional neural network

Building a Convolutional Neural Network (CNN) Model

In this blog, I’ll show how to build CNN model for image classification.

#python #convolutional-neural-net #machine-learning #deep-learning #cnn #programming