Analyzing and Improving the Image Quality of StyleGAN

Karras, Tero; Laine, Samuli; Aittala, Miika; Hellsten, Janne; Lehtinen, Jaakko; Aila, Timo

doi:10.1109/cvpr42600.2020.00813

Cited by 4,901 publications

(5,323 citation statements)

References 9 publications

Supporting

Mentioning

5,283

Contrasting

Unclassified

Order By: Relevance

“…Synthesizing recordings could also act as a potential supplement to real data. Generative Adverserial Nets (GAN) (Goodfellow et al 2014) have for instance proven to produce very lifelike data in other domains such as image generation (e.g., Karras et al 2019). There is an untapped potential to generate virtually unlimited amounts of 'fake' LFPs with similar statistics (power spectrum, temporal correlations, etc.)…”

Section: Discussionmentioning

confidence: 99%

RippleNet: a Recurrent Neural Network for Sharp Wave Ripple (SPW-R) Detection

et al. 2021

View full text Add to dashboard Cite

Hippocampal sharp wave ripples (SPW-R) have been identified as key bio-markers of important brain functions such as memory consolidation and decision making. Understanding their underlying mechanisms in healthy and pathological brain function and behaviour rely on accurate SPW-R detection. In this multidisciplinary study, we propose a novel, self-improving artificial intelligence (AI) detection method in the form of deep Recurrent Neural Networks (RNN) with Long Short-Term memory (LSTM) layers that can learn features of SPW-R events from raw, labeled input data. The approach contrasts conventional routines that typically relies on hand-crafted, heuristic feature extraction and often laborious manual curation. The algorithm is trained using supervised learning on hand-curated data sets with SPW-R events obtained under controlled conditions. The input to the algorithm is the local field potential (LFP), the low-frequency part of extracellularly recorded electric potentials from the CA1 region of the hippocampus. Its output predictions can be interpreted as time-varying probabilities of SPW-R events for the duration of the inputs. A simple thresholding applied to the output probabilities is found to identify times of SPW-R events with high precision. The non-causal, or bidirectional variant of the proposed algorithm demonstrates consistently better accuracy compared to the causal, or unidirectional counterpart. Reference implementations of the algorithm, named ‘RippleNet’, are open source, freely available, and implemented using a common open-source framework for neural networks () and can be easily incorporated into existing data analysis workflows for processing experimental data.

show abstract

Section: Discussionmentioning

confidence: 99%

RippleNet: a Recurrent Neural Network for Sharp Wave Ripple (SPW-R) Detection

et al. 2021

View full text Add to dashboard Cite

show abstract

“…GANs have achieved satisfactory results in areas such as image generation [18], super‐resolution [19], image inpainting [20] and style transfer [21]. A typical GAN consists of two parts: a generator and a discriminator.…”

Section: Related Workmentioning

confidence: 99%

UCT‐GAN: underwater image colour transfer generative adversarial network

2020

View full text Add to dashboard Cite

“…Classical musicians and rock musicians, for example, have differing opinions on what makes music "good". Researchers often resort to surveying a group of people on how pleasing and/or realistic their synthetic music sounds in Figure 1: A sample of the results from StyleGan2, demonstrating the realism achievable in similar machine learning generation tasks [20] order to measure their success. Figure 2 provides an example of the evaluation metrics used by the authors of MidiNet.…”

Section: Motivation For Artificial Music Generationmentioning

confidence: 99%

“…This is one of the reasons VAEs are preferred for latent space manipulation: they have a component in their objective function that encourages a smooth latent space. However, GANs have also exhibited smooth latent spaces which allow for predictable manipulation, as showcased in [5,20,28].…”

Section: Vector Operationsmentioning

confidence: 99%

Latent Walking Techniques for Conditioning GAN-Generated Music

Eisenbeiser¹

2020

2020 11th IEEE Annual Ubiquitous Computing, Electronics &Amp; Mobile Communication Conference (UEMCON)

View full text Add to dashboard Cite

Analyzing and Improving the Image Quality of StyleGAN

Cited by 4,901 publications

References 9 publications

RippleNet: a Recurrent Neural Network for Sharp Wave Ripple (SPW-R) Detection

RippleNet: a Recurrent Neural Network for Sharp Wave Ripple (SPW-R) Detection

UCT‐GAN: underwater image colour transfer generative adversarial network

Latent Walking Techniques for Conditioning GAN-Generated Music

Contact Info

Product

Resources

About