中文
相关论文

相关论文: Riemannian Geometry-Preserving Variational Autoenc…

200 篇论文

Gastrointestinal (GI) imaging via Wireless Capsule Endoscopy (WCE) generates a large number of images requiring manual screening. Deep learning-based Clinical Decision Support (CDS) systems can assist screening, yet their performance relies…

计算机视觉与模式识别 · 计算机科学 2026-02-13 Dimitrios E. Diamantis , Dimitris K. Iakovidis

We introduce MGP-VAE (Multi-disentangled-features Gaussian Processes Variational AutoEncoder), a variational autoencoder which uses Gaussian processes (GP) to model the latent space for the unsupervised learning of disentangled…

计算机视觉与模式识别 · 计算机科学 2020-07-21 Sarthak Bhagat , Shagun Uppal , Zhuyun Yin , Nengli Lim

The variational auto-encoder (VAE) is a popular method for learning a generative model and embeddings of the data. Many real datasets are hierarchically structured. However, traditional VAEs map data in a Euclidean latent space which cannot…

机器学习 · 统计学 2019-11-27 Emile Mathieu , Charline Le Lan , Chris J. Maddison , Ryota Tomioka , Yee Whye Teh

Early detection of Barrett's Esophagus (BE), the only known precursor to Esophageal adenocarcinoma (EAC), is crucial for effectively preventing and treating esophageal cancer. In this work, we investigate the potential of geometric…

图像与视频处理 · 电气工程与系统科学 2025-06-17 Vivien van Veldhuizen , Sharvaree Vadgama , Onno J. de Boer , Sybren Meijer , Erik J. Bekkers

Deep generative models like variational autoencoders approximate the intrinsic geometry of high dimensional data manifolds by learning low-dimensional latent-space variables and an embedding function. The geometric properties of these…

计算机视觉与模式识别 · 计算机科学 2019-02-20 Ankita Shukla , Shagun Uppal , Sarthak Bhagat , Saket Anand , Pavan Turaga

We present an empirical evaluation of fMRI data augmentation via synthesis. For synthesis we use generative mod-els trained on real neuroimaging data to produce novel task-dependent functional brain images. Analyzed generative mod-els…

计算机视觉与模式识别 · 计算机科学 2019-07-16 Peiye Zhuang , Alexander G. Schwing , Sanmi Koyejo

Objective: This paper investigates how generative models, trained on ground-truth images, can be used \changes{as} priors for inverse problems, penalizing reconstructions far from images the generator can produce. The aim is that learned…

图像与视频处理 · 电气工程与系统科学 2023-08-07 Margaret Duff , Ivor J. A. Simpson , Matthias J. Ehrhardt , Neill D. F. Campbell

Decoding of motor imagery (MI) from Electroencephalogram (EEG) is an important component of the Brain-Computer Interface (BCI) system that helps motor-disabled people interact with the outside world via external devices. The main issue in…

信号处理 · 电气工程与系统科学 2022-10-05 Souvik Phadikar , Nidul Sinha , Rajdeep Ghosh

Despite the increasing use of deep learning in medical image segmentation, acquiring sufficient training data remains a challenge in the medical field. In response, data augmentation techniques have been proposed; however, the generation of…

图像与视频处理 · 电气工程与系统科学 2024-06-11 Aghiles Kebaili , Jérôme Lapuyade-Lahorgue , Pierre Vera , Su Ruan

We present a novel graph-based learning of EEG representations with gradient alignment (GEEGA) that leverages multi-domain information to learn EEG representations for brain-computer interfaces. Our model leverages graph convolutional…

人机交互 · 计算机科学 2025-12-09 Prithila Angkan , Amin Jalali , Paul Hungler , Ali Etemad

Variational autoencoders (VAEs) and generative adversarial networks (GANs) enjoy an intuitive connection to manifold learning: in training the decoder/generator is optimized to approximate a homeomorphism between the data distribution and…

机器学习 · 计算机科学 2020-08-28 Henry Li , Ofir Lindenbaum , Xiuyuan Cheng , Alexander Cloninger

Decoding brain activity from electroencephalography (EEG) is crucial for neuroscience and clinical applications. Among recent advances in deep learning for EEG, geometric learning stands out as its theoretical underpinnings on symmetric…

人工智能 · 计算机科学 2026-02-27 Haohui Jia , Zheng Chen , Lingwei Zhu , Xu Cao , Yasuko Matsubara , Takashi Matsubara , Yasushi Sakurai

Separating shared and independent features is crucial for multi-phase contrast-enhanced (CE) MRI synthesis. However, existing methods use deep autoencoder generators with low parameter efficiency and lack interpretable training strategies.…

计算机视觉与模式识别 · 计算机科学 2025-10-06 Xiaoyan Kui , Qianmu Xiao , Qqinsong Li , Zexin Ji , JIelin Zhang , Beiji Zou

This paper proposes a strategy to handle missing data for the classification of electroencephalograms using covariance matrices. It relies on the observed-data likelihood within an expectation-maximization algorithm. This approach is…

人机交互 · 计算机科学 2022-05-06 Alexandre Hippert-Ferrer , Ammar Mian , Florent Bouchard , Frédéric Pascal

Electroencephalography (EEG) has become one of the key modalities underpinning brain-computer interfaces (BCIs) due to its high temporal resolution, rapid responsiveness, non-invasiveness, low cost, and portability. However, EEG signals are…

神经元与认知 · 定量生物学 2026-04-17 Yihang Dong , Changhong Jing , Shuqiang Wang

Ambiguity is inevitable in medical images, which often results in different image interpretations (e.g. object boundaries or segmentation maps) from different human experts. Thus, a model that learns the ambiguity and outputs a probability…

计算机视觉与模式识别 · 计算机科学 2020-10-22 Linchen Qian , Jiasong Chen , Timur Urakov , Weiyong Gu , Liang Liang

Variational autoencoder (VAE) is a widely used generative model for learning latent representations. Burda et al. in their seminal paper showed that learning capacity of VAE is limited by over-pruning. It is a phenomenon where a significant…

机器学习 · 计算机科学 2020-08-10 Rayyan Ahmad Khan , Muhammad Umer Anwaar , Martin Kleinsteuber

Learning disentangled representations leads to interpretable models and facilitates data generation with style transfer, which has been extensively studied on static data such as images in an unsupervised learning framework. However, only a…

机器学习 · 计算机科学 2021-01-20 Jun Han , Martin Renqiang Min , Ligong Han , Li Erran Li , Xuan Zhang

Optimal computations under uncertainty require an adequate probabilistic representation about beliefs. Deep generative models, and specifically Variational Autoencoders (VAEs), have the potential to meet this demand by building latent…

For many Automatic Speech Recognition (ASR) tasks audio features as spectrograms show better results than Mel-frequency Cepstral Coefficients (MFCC), but in practice they are hard to use due to a complex dimensionality of a feature space.…

声音 · 计算机科学 2024-10-07 Olga Iakovenko , Ivan Bondarenko