Quaternion Generative Adversarial Networks
- URL: http://arxiv.org/abs/2104.09630v1
- Date: Mon, 19 Apr 2021 20:46:18 GMT
- Title: Quaternion Generative Adversarial Networks
- Authors: Eleonora Grassucci, Edoardo Cicero, Danilo Comminiello
- Abstract summary: We propose a family of quaternion-valued adversarial networks (QGANs)
QGANs exploit the properties of quaternion algebra, e.g., the Hamilton product for convolutions.
Results show that QGANs are able to generate visually pleasing images and to obtain better FID scores with respect to their real-valued GANs.
- Score: 5.156484100374058
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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 real-valued convolutional networks that flatten and concatenate
the input, losing any intra-channel spatial relation. To address these issues,
here we propose a family of quaternion-valued generative adversarial networks
(QGANs). QGANs exploit the properties of quaternion algebra, e.g., the Hamilton
product for convolutions. This 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 multiple image generation benchmarks. Results show
that QGANs are able to generate visually pleasing images and to obtain better
FID scores with respect to their real-valued GANs. 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.
Related papers
- Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimation [53.91958614666386]
Unsupervised graph representation learning (UGRL) based on graph neural networks (GNNs)
We propose a novel UGRL method based on Multi-hop feature Quality Estimation (MQE)
arXiv Detail & Related papers (2024-07-29T12:24:28Z) - U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation [48.40120035775506]
Kolmogorov-Arnold Networks (KANs) reshape the neural network learning via the stack of non-linear learnable activation functions.
We investigate, modify and re-design the established U-Net pipeline by integrating the dedicated KAN layers on the tokenized intermediate representation, termed U-KAN.
We further delved into the potential of U-KAN as an alternative U-Net noise predictor in diffusion models, demonstrating its applicability in generating task-oriented model architectures.
arXiv Detail & Related papers (2024-06-05T04:13:03Z) - SMaRt: Improving GANs with Score Matching Regularity [94.81046452865583]
Generative adversarial networks (GANs) usually struggle in learning from highly diverse data, whose underlying manifold is complex.
We show that score matching serves as a promising solution to this issue thanks to its capability of persistently pushing the generated data points towards the real data manifold.
We propose to improve the optimization of GANs with score matching regularity (SMaRt)
arXiv Detail & Related papers (2023-11-30T03:05:14Z) - Spider GAN: Leveraging Friendly Neighbors to Accelerate GAN Training [20.03447539784024]
We propose a novel approach for training GANs with images as inputs, but without enforcing any pairwise constraints.
The process can be made efficient by identifying closely related datasets, or a friendly neighborhood'' of the target distribution.
We show that the Spider GAN formulation results in faster convergence, as the generator can discover correspondence even between seemingly unrelated datasets.
arXiv Detail & Related papers (2023-05-12T17:03:18Z) - Auto-Transfer: Learning to Route Transferrable Representations [77.30427535329571]
We propose a novel adversarial multi-armed bandit approach which automatically learns to route source representations to appropriate target representations.
We see upwards of 5% accuracy improvements compared with the state-of-the-art knowledge transfer methods.
arXiv Detail & Related papers (2022-02-02T13:09:27Z) - Quaternion-Based Graph Convolution Network for Recommendation [45.005089037955536]
Graph Convolution Network (GCN) has been widely applied in recommender systems.
GCN is vulnerable to noisy and incomplete graphs, which are common in real world.
We propose a Quaternion-based Graph Convolution Network (QGCN) recommendation model.
arXiv Detail & Related papers (2021-11-20T07:42:18Z) - Global Filter Networks for Image Classification [90.81352483076323]
We present a conceptually simple yet computationally efficient architecture that learns long-term spatial dependencies in the frequency domain with log-linear complexity.
Our results demonstrate that GFNet can be a very competitive alternative to transformer-style models and CNNs in efficiency, generalization ability and robustness.
arXiv Detail & Related papers (2021-07-01T17:58:16Z) - Unpaired Image Enhancement with Quality-Attention Generative Adversarial
Network [92.01145655155374]
We propose a quality attention generative adversarial network (QAGAN) trained on unpaired data.
Key novelty of the proposed QAGAN lies in the injected QAM for the generator.
Our proposed method achieves better performance in both objective and subjective evaluations.
arXiv Detail & Related papers (2020-12-30T05:57:20Z) - A Quaternion-Valued Variational Autoencoder [15.153617649974263]
variational autoencoders (VAEs) have proved their ability in modeling a generative process by learning a latent representation of the input.
We propose a novel VAE defined in the quaternion domain, which exploits the properties of quaternion algebra to improve performance.
arXiv Detail & Related papers (2020-10-22T12:33:42Z) - Generative Adversarial Networks (GANs): An Overview of Theoretical
Model, Evaluation Metrics, and Recent Developments [9.023847175654602]
Generative Adversarial Network (GAN) is an effective method to produce samples of large-scale data distribution.
GANs provide an appropriate way to learn deep representations without widespread use of labeled training data.
In GANs, the generative model is estimated via a competitive process where the generator and discriminator networks are trained simultaneously.
arXiv Detail & Related papers (2020-05-27T05:56:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.