mlsanityData to 7 Oct 2026

Integrative Variational Autoencoders for Generative Modeling of an Image Outcome with Multiple Input Images

arXiv 2402.02734 ↗First posted 5 Feb 2024eess.IV cs.CV cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

Understanding relationships across multiple imaging modalities is central to neuroimaging research. We introduce the Integrative Variational Autoencoder (InVA), the first hierarchical VAE framework for image-on-image regression in multimodal neuroimaging. Unlike standard VAEs, which are not designed for predictive integration across modalities, InVA models outcome images as functions of both shared and modality-specific features. This flexible, data-driven approach avoids rigid assumptions of classical tensor regression and outperforms conventional VAEs and nonlinear models such as BART. As a key application, InVA accurately predicts costly PET scans from structural MRI, offering an efficient and powerful tool for multimodal neuroimaging.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 70 references that are in the map. First posted on arXiv 5 Feb 2024.

Builds on

26 of 70 references.

References · 26

  1. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  2. 2016Variational Inference: A Review for Statisticianscited by 1,466
  3. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  4. 2022Multimodal Learning with Transformers: A Surveycited by 399
  5. 2017Wasserstein Auto-Encoderscited by 371
  6. 2015Generative Moment Matching Networkscited by 252
  7. 2015DRAW: A Recurrent Neural Network For Image Generationcited by 190
  8. 2018Recent Advances in Autoencoder-Based Representation Learningcited by 130
  9. 2020Dynamical Variational Autoencoders: A Comprehensive Reviewcited by 127
  10. 2016HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognitioncited by 103
  11. 2019Unsupervised speech representation learning using WaveNet autoencoderscited by 90
  12. 2015Hierarchical Variational Modelscited by 89
14 more
  1. 2019Learning Hierarchical Priors in VAEscited by 53
  2. 2022A Review on Methods and Applications in Multimodal Deep Learningcited by 29
  3. 2023Geometric Autoencoders -- What You See is What You Decodecited by 23
  4. 2017Tensor-on-tensor regressioncited by 22
  5. 2016Generalized Deep Image to Image Regressioncited by 14
  6. 2020TADPOLE Challenge: Accurate Alzheimer's disease prediction through crowdsourced forecasting of future datacited by 14
  7. 2023Revisiting Structured Variational Autoencoderscited by 11
  8. 2018Multi-Source Neural Variational Inferencecited by 9
  9. 2020Distributed Bayesian Varying Coefficient Modeling Using a Gaussian Process Priorcited by 6
  10. 2022Cooperation in the Latent Space: The Benefits of Adding Mixture Components in Variational Autoencoderscited by 6
  11. 2023Self-Supervised Pre-Training for Deep Image Prior-Based Robust PET Image Denoisingcited by 4
  12. 2022FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusioncited by 3
  13. 2023A tensor based varying-coefficient model for multi-modal neuroimaging data analysiscited by 2
  14. 2023Unscented Autoencodercited by 2

Built on by

Not cited yet.