Exploring Novel Pooling Strategies for Edge Preserved Feature Maps in Convolutional Neural Networks

10/17/2021
by   Adithya Sineesh, et al.
0

With the introduction of anti-aliased convolutional neural networks (CNN), there has been some resurgence in relooking the way pooling is done in CNNs. The fundamental building block of the anti-aliased CNN has been the application of Gaussian smoothing before the pooling operation to reduce the distortion due to aliasing thereby making CNNs shift invariant. Wavelet based approaches have also been proposed as a possibility of additional noise removal capability and gave interesting results for even segmentation tasks. However, all the approaches proposed completely remove the high frequency components under the assumption that they are noise. However, by removing high frequency components, the edges in the feature maps are also smoothed. In this work, an exhaustive analysis of the edge preserving pooling options for classification, segmentation and autoencoders are presented. Two novel pooling approaches are presented such as Laplacian-Gaussian Concatenation with Attention (LGCA) pooling and Wavelet based approximate-detailed coefficient concatenation with attention (WADCA) pooling. The results suggest that the proposed pooling approaches outperform the conventional pooling as well as blur pooling for classification, segmentation and autoencoders.

READ FULL TEXT

page 18

page 20

page 22

page 23

page 24

research
08/06/2018

Detailed Dense Inference with Convolutional Neural Networks via Discrete Wavelet Transform

Dense pixelwise prediction such as semantic segmentation is an up-to-dat...
research
05/31/2022

Hierarchical Spherical CNNs with Lifting-based Adaptive Wavelets for Pooling and Unpooling

Pooling and unpooling are two essential operations in constructing hiera...
research
01/23/2022

Wavelet-Attention CNN for Image Classification

The feature learning methods based on convolutional neural network (CNN)...
research
02/15/2021

How Convolutional Neural Networks Deal with Aliasing

The convolutional neural network (CNN) remains an essential tool in solv...
research
05/07/2020

Wavelet Integrated CNNs for Noise-Robust Image Classification

Convolutional Neural Networks (CNNs) are generally prone to noise interr...
research
07/28/2021

WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification

Though widely used in image classification, convolutional neural network...
research
08/21/2020

Delving Deeper into Anti-aliasing in ConvNets

Aliasing refers to the phenomenon that high frequency signals degenerate...

Please sign up or login with your details

Forgot password? Click here to reset