Recent advances in conditional generative modeling have introduced Continuous conditional Generative Adversarial Network (CcGAN) and Continuous Conditional Diffusion Model (CCDM) for estimating high-dimensional data distributions conditioned on scalar, continuous regression labels (e.g., angles, ages, or temperatures). However, these approaches face fundamental limitations: CcGAN suffers from data imbalance due to fixed-size vicinity constraints, while CCDM requires computationally expensive iterative sampling. To address these issues, we propose CcGAN-AVAR, an enhanced CcGAN framework featuring (1) two novel components for handling data imbalance - an adaptive vicinity mechanism that dynamically adjusts vicinity size and a multi-task discriminator that enhances generator training through auxiliary regression and density ratio estimation - and (2) the GAN framework's native one-step generator, enable 30x-2000x faster inference than CCDM. Extensive experiments on four benchmark datasets (64x64 to 256x256 resolution) across eleven challenging settings demonstrate that CcGAN-AVAR achieves state-of-the-art generation quality while maintaining sampling efficiency.

翻译：条件生成建模的最新进展引入了连续条件生成对抗网络（CcGAN）与连续条件扩散模型（CCDM），用于估计以标量连续回归标签（如角度、年龄或温度）为条件的高维数据分布。然而，这些方法存在根本性局限：CcGAN因固定大小的邻域约束而受数据不平衡问题困扰，而CCDM则需要计算成本高昂的迭代采样。为解决这些问题，我们提出了CcGAN-AVAR，一种增强的CcGAN框架，其特点包括：（1）两个处理数据不平衡的新组件——动态调整邻域大小的自适应邻域机制，以及通过辅助回归与密度比估计来增强生成器训练的多任务判别器；（2）GAN框架固有的单步生成器，其推理速度比CCDM快30至2000倍。在四个基准数据集（分辨率从64x64到256x256）上进行的十一项挑战性设置的广泛实验表明，CcGAN-AVAR在保持采样效率的同时，实现了最先进的生成质量。