Improving GANs using optimal transport
Summary
OT-GAN introduces a novel GAN variant using optimal transport combined with energy distance in an adversarially learned feature space to improve training stability and image generation quality. The method demonstrates state-of-the-art results on benchmark problems with stable training using large mini-batches.
View Cached Full Text
Cached at: 04/20/26, 02:55 PM
Similar Articles
SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport
Proposes SAOT, a structure-aware optimal transport framework for self-supervised continual graph learning that preserves relational structure across tasks. Achieves significant performance gains over state-of-the-art methods on multiple benchmarks, including up to 15% improvement on Products-CL.
Cross-scale Aligned Supervision for Training GANs
This paper proposes CAT, a cross-scale aligned transformer that enforces consistency between intermediate and final GAN outputs to resolve trajectory misalignment, achieving state-of-the-art FID of 1.56 on ImageNet-256.
An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning
This paper introduces MMOT, an online mixture model learning framework based on optimal transport theory that addresses incremental learning with distributional shifts through dynamic centroid updates and improved class similarity estimation. The approach includes a Dynamic Preservation strategy to mitigate catastrophic forgetting and maintain class separability in latent space.
Evolutionary Refinement of Generative Graph Topologies: A Hybrid WGAN-GA Approach
This paper proposes a hybrid WGAN-GA approach for refining generative graph topologies, using a genetic algorithm to correct residual structural deviations in GAN-based generated graphs, improving realism for synthetic graph synthesis and data augmentation.
OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models
OTCache is a training-free framework that uses optimal transport to predict caching schedules for diffusion models, achieving up to 4.7x acceleration on FLUX.1, Qwen-Image, and HunyuanVideo while improving generation fidelity.