Generative Deep Learning

Generative deep learning focuses on using artificial neural networks to create new data instances that resemble a training dataset, aiming to generate realistic and diverse outputs across various domains. Current research emphasizes improving the realism and controllability of generated data, employing architectures like GANs, VAEs, and diffusion models, often incorporating additional knowledge or constraints to address limitations in data quality or domain specificity. This field is significantly impacting diverse areas, from enhancing data privacy through synthetic data generation to accelerating scientific discovery by simulating complex systems and improving image analysis in medical imaging and other fields.

Papers

October 24, 2024

An Investigation on Machine Learning Predictive Accuracy Improvement and Uncertainty Reduction using VAE-based Data Augmentation
Farah Alsafadi, Mahmoud Yaseen, Xu Wu
Data Augmentation Bayesian Neural Network Comprehensive Investigation Generative Deep Learning Nuclear Engineering

October 14, 2024

Generative Deep Learning and Signal Processing for Data Augmentation of Cardiac Auscultation Signals: Improving Model Robustness Using Synthetic Audio
Leigh Abbott, Milan Marocchi, Matthew Fynn, Yue Rong, Sven Nordholm
Native Robustness Data Augmentation Audio Driven Signal Processing Robust Classifier Generative Deep Learning Heart Sound Classification

September 25, 2024

KIPPS: Knowledge infusion in Privacy Preserving Synthetic Data Generation
Anantaa Kotal, Anupam Joshi
Synthetic Data Synthetic Data Generation Private Synthetic Data Generation Generative Deep Learning Knowledge Infusion User Configurable Privacy Defense

April 22, 2024

LVNS-RAVE: Diversified audio generation with RAVE and Latent Vector Novelty Search
Jinyue Guo, Anna-Maria Christodoulou, Balint Laczko, Kyrre Glette
Pre Trained Model Audio Generation Generative Deep Learning Audio Generation Task

March 18, 2024

December 23, 2023

Towards End-to-End Structure Solutions from Information-Compromised Diffraction Data via Generative Deep Learning
Gabe Guo, Judah Goldfeder, Ling Lan, Aniv Ray, Albert Hanming Yang, Boyuan Chen, Simon JL Billinge, Hod Lipson
Structural Information Generative Deep Learning Diffraction Pattern Structure Property Relationship Powder X Ray Diffraction Serial Femtosecond Crystallography

December 4, 2023

Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images
Zhuoran Yu, Chenchen Zhu, Sean Culatana, Raghuraman Krishnamoorthi, Fanyi Xiao, Yong Jae Lee
Generative Model Fine Tuning Synthetic Image Generative Deep Learning Synthetic Training Image

May 12, 2023

A stable deep adversarial learning approach for geological facies generation
Ferdinand Bhavsar, Nicolas Desassis, Fabien Ors, Thomas Romary
Generative Adversarial Network Generative Deep Learning Generative Deep Learning Approach

May 4, 2023

A Generative Modeling Framework for Inferring Families of Biomechanical Constitutive Laws in Data-Sparse Regimes
Minglang Yin, Zongren Zou, Enrui Zhang, Cristina Cavinato, Jay D. Humphrey, George Em Karniadakis
Generative Adversarial Network Generative Framework Constitutive Model Low Data Regime Generative Deep Learning Model Family

April 23, 2023

DiffESM: Conditional Emulation of Earth System Models with Diffusion Models
Seth Bassetti, Brian Hutchinson, Claudia Tebaldi, Ben Kravitz
Diffusion Model Earth System Model Generative Deep Learning Climate Scenario

April 11, 2023

Modeling and design of heterogeneous hierarchical bioinspired spider web structures using generative deep learning and additive manufacturing
Wei Lu, Nic A. Lee, Markus J. Buehler
Product Design Generative Deep Learning Web Graph

March 16, 2023

Exploring the Power of Generative Deep Learning for Image-to-Image Translation and MRI Reconstruction: A Cross-Domain Review
Yuda Bi
Deep Learning Generative Adversarial Network Real Power Cross Domain Image to Image Translation Generative Image Model Generative Deep Learning Medical Generative

December 1, 2022

Human-instructed Deep Hierarchical Generative Learning for Automated Urban Planning
Dongjie Wang, Lingfei Wu, Denghui Zhang, Jingbo Zhou, Leilei Sun, Yanjie Fu
Layout Generation Generative Deep Learning Urban Prediction Hierarchical Deep Generative

September 26, 2022

Automated Urban Planning aware Spatial Hierarchies and Human Instructions
Dongjie Wang, Kunpeng Liu, Yanyong Huang, Leilei Sun, Bowen Du, Yanjie Fu
Human Instruction Urban Planning Generative Deep Learning

August 17, 2022

Deep Generative Views to Mitigate Gender Classification Bias Across Gender-Race Groups
Sreeraj Ramachandran, Ajita Rattani
Bias Mitigation Gender Prediction Gender Classification Generative Deep Learning Gender Classification Bias Intersectional Group

March 29, 2022

A Sparsity-promoting Dictionary Model for Variational Autoencoders
Mostafa Sadeghi, Paul Magron
Latent Space Variational Autoencoders Generative Deep Learning Gaussian Latent

March 2, 2022

VAE-iForest: Auto-encoding Reconstruction and Isolation-based Anomalies Detecting Fallen Objects on Road Surface
Takato Yasuno, Junichiro Fujii, Riku Ogata, Masahiro Okano
Arbitrary Object Full State Reconstruction Generative Deep Learning Road Condition Monitoring Isolation Based Anomaly

February 23, 2022

Synthesizing Photorealistic Images with Deep Generative Learning
Chuanxia Zheng
Image Synthesis Image Translation Image Completion Photorealistic Image Scene Decomposition Generative Deep Learning Visual Synthesis

December 26, 2021

Automated Urban Planning for Reimagining City Configuration via Adversarial Learning: Quantification, Generation, and Evaluation
Dongjie Wang, Yanjie Fu, Kunpeng Liu, Fanglan Chen, Pengyang Wang, Chang-Tien Lu
Faithful Generation Adversarial Learning Land Use Urban Planning Generative Deep Learning Urban Layout

Generative Deep Learning

Papers

An Investigation on Machine Learning Predictive Accuracy Improvement and Uncertainty Reduction using VAE-based Data Augmentation

Generative Deep Learning and Signal Processing for Data Augmentation of Cardiac Auscultation Signals: Improving Model Robustness Using Synthetic Audio

KIPPS: Knowledge infusion in Privacy Preserving Synthetic Data Generation

LVNS-RAVE: Diversified audio generation with RAVE and Latent Vector Novelty Search

Adaptive LPD Radar Waveform Design with Generative Deep Learning

Synthetic Image Generation in Cyber Influence Operations: An Emergent Threat?

Towards End-to-End Structure Solutions from Information-Compromised Diffraction Data via Generative Deep Learning

Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images

A stable deep adversarial learning approach for geological facies generation

A Generative Modeling Framework for Inferring Families of Biomechanical Constitutive Laws in Data-Sparse Regimes

DiffESM: Conditional Emulation of Earth System Models with Diffusion Models

Modeling and design of heterogeneous hierarchical bioinspired spider web structures using generative deep learning and additive manufacturing

Exploring the Power of Generative Deep Learning for Image-to-Image Translation and MRI Reconstruction: A Cross-Domain Review

Human-instructed Deep Hierarchical Generative Learning for Automated Urban Planning

Automated Urban Planning aware Spatial Hierarchies and Human Instructions

Deep Generative Views to Mitigate Gender Classification Bias Across Gender-Race Groups

A Sparsity-promoting Dictionary Model for Variational Autoencoders

VAE-iForest: Auto-encoding Reconstruction and Isolation-based Anomalies Detecting Fallen Objects on Road Surface

Synthesizing Photorealistic Images with Deep Generative Learning

Automated Urban Planning for Reimagining City Configuration via Adversarial Learning: Quantification, Generation, and Evaluation