# Stochastic Conditional Generative Networks with Basis Decomposition

arXiv: https://arxiv.org/abs/1909.11286 · HTML: https://mlsanity.com/paper/1909.11286/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2019.

## Built on by (most cited first, 9 of 9)

- [Large Scale Image Completion via Co-Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2103.10428/) (2021)
- [Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization](https://mlsanity.com/paper/2410.03190/) (2024)
- [Adaptive Convolutions with Per-pixel Dynamic Filter Atom](https://mlsanity.com/paper/2108.07895/) (2021)
- [CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-to-Image Generation](https://mlsanity.com/paper/2107.13516/) (2021)
- [Generative Memory-Guided Semantic Reasoning Model for Image Inpainting](https://mlsanity.com/paper/2110.00261/) (2021)
- [Semantics-aware Multi-modal Domain Translation:From LiDAR Point Clouds to Panoramic Color Images](https://mlsanity.com/paper/2106.13974/) (2021)
- [Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models](https://mlsanity.com/paper/2503.18337/) (2025)
- [Generative Quanta Color Imaging](https://mlsanity.com/paper/2403.19066/) (2024)
- [Sparse Fine-Tuning of Transformers for Generative Tasks](https://mlsanity.com/paper/2507.10855/) (2025)

## Abstract (arXiv)

While generative adversarial networks (GANs) have revolutionized machine learning, a number of open questions remain to fully understand them and exploit their power. One of these questions is how to efficiently achieve proper diversity and sampling of the multi-mode data space. To address this, we introduce BasisGAN, a stochastic conditional multi-mode image generator. By exploiting the observation that a convolutional filter can be well approximated as a linear combination of a small set of basis elements, we learn a plug-and-played basis generator to stochastically generate basis elements, with just a few hundred of parameters, to fully embed stochasticity into convolutional filters. By sampling basis elements instead of filters, we dramatically reduce the cost of modeling the parameter space with no sacrifice on either image diversity or fidelity. To illustrate this proposed plug-and-play framework, we construct variants of BasisGAN based on state-of-the-art conditional image generation networks, and train the networks by simply plugging in a basis generator, without additional auxiliary components, hyperparameters, or training objectives. The experimental success is complemented with theoretical results indicating how the perturbations introduced by the proposed sampling of basis elements can propagate to the appearance of generated images.