# Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input Mechanisms

arXiv: https://arxiv.org/abs/2011.07466 · HTML: https://mlsanity.com/paper/2011.07466/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2020.

## Built on by (most cited first, 20 of 20)

- [CAT: Content-Adaptive Image Tokenization](https://mlsanity.com/paper/2501.03120/) (2025)
- [TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training](https://mlsanity.com/paper/2501.04765/) (2025)
- [Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling](https://mlsanity.com/paper/2310.06389/) (2023)
- [Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and Regression](https://mlsanity.com/paper/2104.03164/) (2021)
- [CCDM: Continuous Conditional Diffusion Models for Image Generation](https://mlsanity.com/paper/2405.03546/) (2024)
- [Efficient Subsampling of Realistic Images From GANs Conditional on a Class or a Continuous Variable](https://mlsanity.com/paper/2103.11166/) (2021)
- [Multi-StyleGS: Stylizing Gaussian Splatting with Multiple Styles](https://mlsanity.com/paper/2506.06846/) (2025)
- [Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2308.10273/) (2023)
- [Regression-Oriented Knowledge Distillation for Lightweight Ship Orientation Angle Prediction with Optical Remote Sensing Images](https://mlsanity.com/paper/2307.06566/) (2023)
- [Synthesizing Forestry Images Conditioned on Plant Phenotype Using a Generative Adversarial Network](https://mlsanity.com/paper/2307.03789/) (2023)
- [Counterfactual Explanation for Regression via Disentanglement in Latent Space](https://mlsanity.com/paper/2311.08228/) (2023)
- [A Generative Model for Accelerated Inverse Modelling Using a Novel Embedding for Continuous Variables](https://mlsanity.com/paper/2311.11343/) (2023)
- [Deep Generative Model-based Synthesis of Four-bar Linkage Mechanisms with Target Conditions](https://mlsanity.com/paper/2402.14882/) (2024)
- [Guiding Token-Sparse Diffusion Models](https://mlsanity.com/paper/2601.01608/) (2026)
- [A CGAN-LSTM-Based Framework for Time-Varying Non-Stationary Channel Modeling](https://mlsanity.com/paper/2503.13468/) (2025)
- [Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinal Learning and Auxiliary Regularization](https://mlsanity.com/paper/2508.01725/) (2025)
- [Reducing Domain Gap with Diffusion-Based Domain Adaptation for Cell Counting](https://mlsanity.com/paper/2512.11763/) (2025)
- [Physics Guided Conditional Diffusion Framework for Generative Inverse Design of Manufacturable Metasurface based Absorbers](https://mlsanity.com/paper/2605.19611/) (2026)
- [Inverse Design of Realizable Metasurface based Absorbers using Improved Conditioning and Diversity Enhanced Progressively Growing GANs](https://mlsanity.com/paper/2606.05849/) (2026)
- [Opening the Black Box of Classifier-Free Guidance via Information Bottleneck](https://mlsanity.com/paper/2610.13369/) (2026)

## Abstract (arXiv)

This work proposes the continuous conditional generative adversarial network (CcGAN), the first generative model for image generation conditional on continuous, scalar conditions (termed regression labels). Existing conditional GANs (cGANs) are mainly designed for categorical conditions (eg, class labels); conditioning on regression labels is mathematically distinct and raises two fundamental problems:(P1) Since there may be very few (even zero) real images for some regression labels, minimizing existing empirical versions of cGAN losses (aka empirical cGAN losses) often fails in practice;(P2) Since regression labels are scalar and infinitely many, conventional label input methods are not applicable. The proposed CcGAN solves the above problems, respectively, by (S1) reformulating existing empirical cGAN losses to be appropriate for the continuous scenario; and (S2) proposing a naive label input (NLI) method and an improved label input (ILI) method to incorporate regression labels into the generator and the discriminator. The reformulation in (S1) leads to two novel empirical discriminator losses, termed the hard vicinal discriminator loss (HVDL) and the soft vicinal discriminator loss (SVDL) respectively, and a novel empirical generator loss. The error bounds of a discriminator trained with HVDL and SVDL are derived under mild assumptions in this work. Two new benchmark datasets (RC-49 and Cell-200) and a novel evaluation metric (Sliding Fr'echet Inception Distance) are also proposed for this continuous scenario. Our experiments on the Circular 2-D Gaussians, RC-49, UTKFace, Cell-200, and Steering Angle datasets show that CcGAN is able to generate diverse, high-quality samples from the image distribution conditional on a given regression label. Moreover, in these experiments, CcGAN substantially outperforms cGAN both visually and quantitatively.