CoDeGAN: Contrastive Disentanglement for Generative Adversarial Network
Disentanglement, a critical concern in interpretable machine learning, has also garnered significant attention from the computer vision community. Many existing GAN-based class disentanglement (unsupervised) approaches, such as InfoGAN and its variants, primarily aim to maximize the mutual information (MI) between the generated image and its latent codes. However, this focus may lead to a tendency for the network to generate highly similar images when presented with the same latent class factor, potentially resulting in mode collapse or mode dropping. To alleviate this problem, we propose \texttt{CoDeGAN} (Contrastive Disentanglement for Generative Adversarial Networks), where we relax similarity constraints for disentanglement from the image domain to the feature domain. This modification not only enhances the stability of GAN training but also improves their disentangling capabilities. Moreover, we integrate self-supervised pre-training into CoDeGAN to learn semantic representations, significantly facilitating unsupervised disentanglement. Extensive experimental results demonstrate the superiority of our method over state-of-the-art approaches across multiple benchmarks. The code is available at https://github.com/learninginvision/CoDeGAN.
Code (1)
Tasks
Contrastive LearningDisentanglementGenerative Adversarial NetworkInterpretable Machine LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Inductive-Biases for Contrastive Learning of Disentangled Representations
Learning disentangled representations is a core machine learning task. It has been shown that this task requires inductive biases. Recent work on class-content disentanglement has shown excellent performance, but require…
Contrastive LearningDisentanglementRepresentation LearningRetrieval+1Representation Disentanglement in Generative Models with Contrastive Learning
Contrastive learning has shown its effectiveness in image classification and generation. Recent works apply the contrastive learning on the discriminator of the Generative Adversarial Networks, and there exists little wo…
Contrastive LearningDisentanglementimage-classificationImage ClassificationInfoGAN-CR: Disentangling Generative Adversarial Networks with Contrastive Regularizers
Standard deep generative models have latent codes that can be arbitrarily rotated, and a specific coordinate has no meaning. For manipulation and exploration of the samples, we seek a disentangled latent code where each …
DisentanglementModel SelectionImproving SCGAN's Similarity Constraint and Learning a Better Disentangled Representation
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 comprehe…
DisentanglementRepresentation LearningSSIMInfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
Disentangled generative models map a latent code vector to a target space, while enforcing that a subset of the learned latent codes are interpretable and associated with distinct properties of the target distribution. R…
DisentanglementModel Selection