The Level Weighted Structural Similarity Loss: A Step Away from the MSE

• Main Author: Lu, Yingjing
• Format: Journal Article
• Language: English
• Published: 30-04-2019
• Subjects: Computer Science - Computer Vision and Pattern Recognition; Computer Science - Learning
• DOI: 10.48550/arxiv.1904.13362

The Mean Square Error (MSE) has shown its strength when applied in deep
generative models such as Auto-Encoders to model reconstruction loss. However,
in image domain especially, the limitation of MSE is obvious: it assumes pixel
independence and ignores spatial relationships of samples. This contradicts
most architectures of Auto-Encoders which use convolutional layers to extract
spatial dependent features. We base on the structural similarity metric (SSIM)
and propose a novel level weighted structural similarity (LWSSIM) loss for
convolutional Auto-Encoders. Experiments on common datasets on various
Auto-Encoder variants show that our loss is able to outperform the MSE loss and
the Vanilla SSIM loss. We also provide reasons why our model is able to succeed
in cases where the standard SSIM loss fails.