Papers › Quaternion Generative Adversarial Networks
Quaternion Generative Adversarial Networks
Eleonora Grassucci, Edoardo Cicero, Danilo Comminiello
Latest Generative Adversarial Networks (GANs) are gathering outstanding results through a large-scale training, thus employing models composed of millions of parameters requiring extensive computational capabilities. Building such huge models undermines their replicability and increases the training instability. Moreover, multi-channel data, such as images or audio, are usually processed by realvalued convolutional networks that flatten and concatenate the input, often losing intra-channel spatial relations. To address these issues related to complexity and information loss, we propose a family of quaternion-valued generative adversarial networks (QGANs). QGANs exploit the properties of quaternion algebra, e.g., the Hamilton product, that allows to process channels as a single entity and capture internal latent relations, while reducing by a factor of 4 the overall number of parameters. We show how to design QGANs and to extend the proposed approach even to advanced models.We compare the proposed QGANs with real-valued counterparts on several image generation benchmarks. Results show that QGANs are able to obtain better FID scores than real-valued GANs and to generate visually pleasing images. Furthermore, QGANs save up to 75% of the training parameters. We believe these results may pave the way to novel, more accessible, GANs capable of improving performance and saving computational resources.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="2104.09630", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2104.09630")
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Generation | CIFAR-10 | QSNGAN | FID | 31.966 | #69 of 78 | Archive leaderboard | report |
| Image Generation | CelebA-HQ 128x128 | QSNGAN | FID | 29.417 | #7 of 7 | Archive leaderboard | report |
| Image Generation | CelebA-HQ 128x128 | QSNGAN | IS | 2.249 | #7 of 7 | Archive leaderboard | report |
| Image Generation | Oxford 102 Flowers 128x128 | QSNGAN | FID | 115.838 | #1 of 1 | Archive leaderboard | report |
| Image Generation | Oxford 102 Flowers 128x128 | QSNGAN | IS | 3 | #1 of 1 | Archive leaderboard | report |
| Image Generation | STL-10 | QSNGAN | FID | 59.611 | #30 of 31 | Archive leaderboard | report |
| Image Generation | STL-10 | QSNGAN | Inception score | 4.987 | #30 of 31 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections