Spatial Frequency Loss for Learning Convolutional Autoencoders

06/06/2018
by   Naoyuki Ichimura, et al.
0

This paper presents a learning method for convolutional autoencoders (CAEs) for extracting features from images. CAEs can be obtained by utilizing convolutional neural networks to learn an approximation to the identity function in an unsupervised manner. The loss function based on the pixel loss (PL) that is the mean squared error between the pixel values of original and reconstructed images is the common choice for learning. However, using the loss function leads to blurred reconstructed images. A method for learning CAEs using a loss function computed from features reflecting spatial frequencies is proposed to mitigate the problem. The blurs in reconstructed images show lack of high spatial frequency components mainly constituting edges and detailed textures that are important features for tasks such as object detection and spatial matching. In order to evaluate the lack of components, a convolutional layer with a Laplacian filter bank as weights is added to CAEs and the mean squared error of features in a subband, called the spatial frequency loss (SFL), is computed from the outputs of each filter. The learning is performed using a loss function based on the SFL. Empirical evaluation demonstrates that using the SFL reduces the blurs in reconstructed images.

READ FULL TEXT
research
10/30/2017

Learning to solve inverse problems using Wasserstein loss

We propose using the Wasserstein loss for training in inverse problems. ...
research
11/08/2020

Frequency Gating: Improved Convolutional Neural Networks for Speech Enhancement in the Time-Frequency Domain

One of the strengths of traditional convolutional neural networks (CNNs)...
research
08/10/2020

Predicting Coordinated Actuated Traffic Signal Change Times using LSTM Neural Networks

Vehicle acceleration and deceleration maneuvers at traffic signals resul...
research
01/15/2022

Concise Logarithmic Loss Function for Robust Training of Anomaly Detection Model

Recently, deep learning-based algorithms are widely adopted due to the a...
research
03/15/2017

Illuminant Estimation using Ensembles of Multivariate Regression Trees

White balancing is a fundamental step in the image processing pipeline. ...
research
11/29/2019

VIABLE: Fast Adaptation via Backpropagating Learned Loss

In few-shot learning, typically, the loss function which is applied at t...
research
08/28/2017

On denoising autoencoders trained to minimise binary cross-entropy

Denoising autoencoders (DAEs) are powerful deep learning models used for...

Please sign up or login with your details

Forgot password? Click here to reset