mlsanityData to 7 Oct 2026

Improving SCGAN's Similarity Constraint and Learning a Better Disentangled Representation

arXiv 2310.12262 ↗First posted 18 Oct 2023cs.CV cs.LG eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

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

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 32 references that are in the map. First posted on arXiv 18 Oct 2023.

Builds on

18 of 32 references.

References · 18

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2016Improved Techniques for Training GANscited by 2,938
  6. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  7. 2020Supervised Contrastive Learningcited by 2,803
  8. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  9. 2014Conditional Generative Adversarial Netscited by 2,152
  10. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  11. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  12. 2018Disentangling by Factorisingcited by 614
6 more
  1. 2016Ladder Variational Autoencoderscited by 315
  2. 2020Inductive Biases for Deep Learning of Higher-Level Cognitioncited by 273
  3. 2018Learning Deep Disentangled Embeddings with the F-Statistic Losscited by 101
  4. 2017Learning Disentangled Representations with Semi-Supervised Deep Generative Modelscited by 72
  5. 2021Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representationscited by 24
  6. 2021CoDeGAN: Contrastive Disentanglement for Generative Adversarial Networkcited by 2

Built on by

Not cited yet.