InfoMax-GAN: Improved Adversarial Image Generation via Information Maximization and Contrastive Learning

By Kwot Sin Lee, Ngoc-Trung Tran, Ngai-Man Cheung. 2020

85 citations recorded by the source corpus.

While Geerative Adversarial Networks (GANs) are fundamental to many generative modelling applications, they suffer from numerous issues. In this work, we propose a principled framework to simultaneously mitigate two fundamental issues in GANs: catastrophic forgetting of the discriminator and mode collapse of the generator. We achieve this by employing for GANs a contrastive learning and mutual information maximization approach, and perform extensive analyses to understand sources of improvements. Our approach significantly stabilizes GAN training and improves GAN performance for image synthesis across five datasets under the same training and evaluation conditions against state-of-the-art works. In particular, compared to the state-of-the-art SSGAN, our approach does not suffer from poorer performance on image domains such as faces, and instead improves performance significantly. Our approach is simple to implement and practical: it involves only one auxiliary objective, has low computational cost, and performs robustly across a wide range of training settings and datasets without any hyperparameter tuning. For reproducibility, our code is available in the open-source GAN library, Mimicry [34].

Subfields: Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

Cross-Modal Contrastive Learning for Text-to-Image Generation (2021, background): “It has been explored under several adversarial training scenarios [25, 65, 9, 41].”
A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “Similarly, resolving within-task catastrophic forgetting can facilitate reinforcement learning [299], [300] and stabilize the training of GANs [301], [302].”
Training GANs with Stronger Augmentations via Contrastive Discriminator (2021, methodology): “Self-supervised learning, including contrastive learning, have been recently applied in GAN as an auxiliary task upon the GAN loss (Chen et al., 2019; Tran et al., 2019; Lee et al., 2021; Zhao et al., 2020d), mainly in attempt to alleviate catastopic forgetting in discriminators (Chen et al., 2019).”
Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Domain Learning (2024, unknown): “AttGAN BEGAN CramerGAN InfoMaxGAN MMDGAN RelGAN S3GAN SNGAN STGAN Mean Acc.”
Dual Contrastive Loss and Attention for GANs (2021, background): “It is orthogonal to [40, 106, 36, 47] where their contrastive losses serve only as an incremental auxiliary to the conventional adversarial loss, apply to the generator rather than the discriminator, and/or require expensive class annotations or augmentation for generation.”