Improving SCGAN's Similarity Constraint and Learning a Better Disentangled Representation
This work addresses the challenge of learning better disentangled representations in generative adversarial networks, which is incremental as it builds upon SCGAN with specific modifications.
The authors tackled the problem of improving disentangled representation learning in SCGAN by modifying its similarity constraint to use SSIM and contrastive loss principles, resulting in better performance on FID and FactorVAE metrics and improved generalizability.
SCGAN adds a similarity constraint between generated images and conditions as a regularization term on generative adversarial networks. Similarity constraint works as a tutor to instruct the generator network to comprehend the difference of representations based on conditions. We understand how SCGAN works on a deeper level. This understanding makes us realize that the similarity constraint functions like the contrastive loss function. We believe that a model with high understanding and intelligence measures the similarity between images based on their structure and high level features, just like humans do. Two major changes we applied to SCGAN in order to make a modified model are using SSIM to measure similarity between images and applying contrastive loss principles to the similarity constraint. The modified model performs better using FID and FactorVAE metrics. The modified model also has better generalisability compared to other models. Keywords Generative Adversarial Nets, Unsupervised Learning, Disentangled Representation Learning, Contrastive Disentanglement, SSIM