LARGE: Latent-Based Regression through GAN Semantics

Nitzan, Yotam; Gal, Ran; Ofir, Brenner,; Cohen–Or, Daniel

doi:10.1109/cvpr52688.2022.01864

Cited by 11 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To investigate how GAN capture high-order relations, we study the encoding of important semantics in the latent space of GAN. GANs have been extremely successful at encoding important semantics about data in entirely unsupervised experimental setup [41]. It has been shown that several semantics emerge in the latent space of GAN during training [42].…”

Section: Methodsmentioning

confidence: 99%

“…It has been shown that several semantics emerge in the latent space of GAN during training [42]. The semantic encoding illustrates smooth and linear directions that affect properties of data (time-points and cell-lineages) w.r.t latent space variables [41]. Researchers have emphasized the importance of establishing interpretable connections between GAN’s latent space variables and meaningful data semantics.…”

Section: Methodsmentioning

confidence: 99%

Section: Latent Space Interpretation Schemesmentioning

confidence: 99%

See 2 more Smart Citations

Hidden Knowledge Recovery from GAN-generated Single-cell RNA-seq Data

Shah,

Li,

Zhang

2023

Preprint

View full text Add to dashboard Cite

BackgroundMachine learning methods have recently been shown powerful in discovering knowledge from scientific data, offering promising prospects for discovery learning. In the meanwhile, Deep Generative Models like Generative Adversarial Networks (GANs) have excelled in generating synthetic data close to real data. GANs have been extensively employed, primarily motivated by generating synthetic data for privacy preservation, data augmentation, etc. However, certain dimensions of GANs have received limited exploration in current literature. Existing studies predominantly utilize huge datasets, presenting a challenge when dealing with limited, complex datasets. Researchers have high-lighted the ineffectiveness of conventional scores for selecting optimal GANs on limited datasets that exhibit complex high order relationships. Furthermore, current methods evaluate GAN’s performance by comparing synthetic data to real data without assessing the preservation of high-order relationships. Researchers have advocated for more objective GAN evaluation techniques and emphasized the importance of establishing interpretable connections between GAN latent space variables and meaningful data semantics.ResultsIn this study, we used a custom GAN model to generate quality synthetic data for a very limited, complex biological dataset. We successfully recovered cell-lineage developmental story from synthetic data using the ab-initio knowledge discovery method, we previously developed. Our custom GAN model performed better than state-of-the-art cscGAN model, when evaluated for recovering hidden knowledge from limited, complex dataset. Then we devise a temporal dataset specific quantitative scoring mechanism to successfully reproduce GAN results for human and mouse embryonic datasets. Our Latent Space Interpretation (LSI) scheme was able to identify anomalies. We also found that the latent space in GAN effectively captured the semantic information and may be used to interpolate data when the sampling of real data is sparse.ConclusionIn summary we used a customized GAN model to generate synthetic data for limited, complex dataset and compared the results with state-of-the-art cscGAN model. Cell-lineage developmental story is recovered as hidden knowledge to evaluate GAN for preserving complex high-order relationships. We formulated a quantitative score to successfully reproduce results on human and mouse embryonic datasets. We designed a LSI scheme to identify anomalies and understand the mechanism by which GAN captures important data semantics in its latent space.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Hidden Knowledge Recovery from GAN-generated Single-cell RNA-seq Data

Shah,

Li,

Zhang

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…These models transform a certain vector space, denoted as the latent space, which can be learned as done in StyleGAN [101][102][103] or GLIDE [104], into the space of desired generated images. The latent space has desirable properties, which allow performing manipulations on it, that can lead to solving inverse problems [105][106][107][108][109][110][111], to having a good representation for classification [112][113][114][115][116][117], or to intuitive image editing [118][119][120][121][122][123][124]. Specifically, for the classification task, the latent space of these models has been used for performing regression of some properties such as age or face pose from a small number of examples [113], for getting a consistent semantic segmentation of parts in generated objects for improving performance on real data [114][115][116], or for efficiently getting data annotation that leads to more efficient training [117].…”

Section: Generative Modelsmentioning

confidence: 99%

Deep learning in optics—a tutorial

Hadad,

Froim,

Yosef

et al. 2023

J. Opt.

View full text Add to dashboard Cite

In recent years, machine learning and deep neural networks applications have experienced a remarkable surge in the field of physics, with optics being no exception. This tutorial aims to offer a fundamental introduction to the utilization of deep learning in optics, catering specifically to newcomers. Within this tutorial, we cover essential concepts, survey the field, and provide guidelines for the creation and deployment of artificial neural network architectures tailored to optical problems.

show abstract