中文
相关论文

相关论文: Invariance-based Multi-Clustering of Latent Space …

200 篇论文

Despite advances in deep probabilistic models, learning discrete latent representations remains challenging. This work introduces a novel method to improve inference in discrete Variational Autoencoders by reframing the inference problem…

机器学习 · 计算机科学 2025-06-11 María Martínez-García , Grace Villacrés , David Mitchell , Pablo M. Olmos

Disentanglement learning is central to understanding and reusing learned representations in variational autoencoders (VAEs). Although equivariance has been explored in this context, effectively exploiting it for disentanglement remains…

机器学习 · 计算机科学 2026-02-06 Hee-Jun Jung , Jaehyoung Jeong , Kangil Kim

With the ever-increasing amount of data, the central challenge in multimodal learning involves limitations of labelled samples. For the task of classification, techniques such as meta-learning, zero-shot learning, and few-shot learning…

计算机视觉与模式识别 · 计算机科学 2021-06-29 Nihar Bendre , Kevin Desai , Peyman Najafirad

Deep learning approaches process data in a layer-by-layer way with intermediate (or latent) features. We aim at designing a general solution to optimize the latent manifolds to improve the performance on classification, segmentation,…

机器学习 · 计算机科学 2025-06-03 Yida Wang , David Joseph Tan , Nassir Navab , Federico Tombari

We present new intuitions and theoretical assessments of the emergence of disentangled representation in variational autoencoders. Taking a rate-distortion theory perspective, we show the circumstances under which representations aligned…

Variational auto-encoders (VAE) are popular deep latent variable models which are trained by maximizing an Evidence Lower Bound (ELBO). To obtain tighter ELBO and hence better variational approximations, it has been proposed to use…

机器学习 · 统计学 2021-07-22 Achille Thin , Nikita Kotelevskii , Arnaud Doucet , Alain Durmus , Eric Moulines , Maxim Panov

We view disentanglement learning as discovering an underlying structure that equivariantly reflects the factorized variations shown in data. Traditionally, such a structure is fixed to be a vector space with data variations represented by…

机器学习 · 计算机科学 2021-06-08 Xinqi Zhu , Chang Xu , Dacheng Tao

This paper describes InfoCatVAE, an extension of the variational autoencoder that enables unsupervised disentangled representation learning. InfoCatVAE uses multimodal distributions for the prior and the inference network and then maximizes…

机器学习 · 计算机科学 2018-06-26 Edouard Pineau , Marc Lelarge

Variational autoencoders (VAEs), that are built upon deep neural networks have emerged as popular generative models in computer vision. Most of the work towards improving variational autoencoders has focused mainly on making the…

机器学习 · 统计学 2016-11-17 Siddharth Agrawal , Ambedkar Dukkipati

Latent generative models have emerged as a leading approach for high-quality image synthesis. These models rely on an autoencoder to compress images into a latent space, followed by a generative model to learn the latent distribution. We…

机器学习 · 计算机科学 2025-08-05 Theodoros Kouzelis , Ioannis Kakogeorgiou , Spyros Gidaris , Nikos Komodakis

When trained effectively, the Variational Autoencoder (VAE) is both a powerful language model and an effective representation learning framework. In practice, however, VAEs are trained with the evidence lower bound (ELBO) as a surrogate…

机器学习 · 计算机科学 2019-09-04 Bohan Li , Junxian He , Graham Neubig , Taylor Berg-Kirkpatrick , Yiming Yang

We combine conditional variational autoencoders (VAE) with adversarial censoring in order to learn invariant representations that are disentangled from nuisance/sensitive variations. In this method, an adversarial network attempts to…

机器学习 · 计算机科学 2018-05-22 Ye Wang , Toshiaki Koike-Akino , Deniz Erdogmus

Learning Interpretable representation in medical applications is becoming essential for adopting data-driven models into clinical practice. It has been recently shown that learning a disentangled feature representation is important for a…

机器学习 · 计算机科学 2019-04-19 Mhd Hasan Sarhan , Abouzar Eslami , Nassir Navab , Shadi Albarqouni

Learning a disentangled, interpretable, and structured latent representation in 3D generative models of faces and bodies is still an open problem. The problem is particularly acute when control over identity features is required. In this…

计算机视觉与模式识别 · 计算机科学 2022-03-25 Simone Foti , Bongjin Koo , Danail Stoyanov , Matthew J. Clarkson

We develop Riemannian approaches to variational autoencoders (VAEs) for PDE-type ambient data with regularizing geometric latent dynamics, which we refer to as VAE-DLM, or VAEs with dynamical latent manifolds. We redevelop the VAE framework…

机器学习 · 计算机科学 2026-01-21 Andrew Gracyk

Co-clustering exploits the duality of instances and features to simultaneously uncover meaningful groups in both dimensions, often outperforming traditional clustering in high-dimensional or sparse data settings. Although recent deep…

机器学习 · 计算机科学 2025-04-10 Ashwin Vinod , Chandrajit Bajaj

Disentangled representations enable models to separate factors of variation that are shared across experimental conditions from those that are condition-specific. This separation is essential in domains such as biomedical data analysis,…

机器学习 · 计算机科学 2025-12-16 Yuli Slavutsky , Ozgur Beker , David Blei , Bianca Dumitrascu

Variational autoencoders (VAEs) are one class of generative probabilistic latent-variable models designed for inference based on known data. They balance reconstruction and regularizer terms. A variational approximation produces an evidence…

机器学习 · 统计学 2023-12-13 Robert I. Cukier

The ability of Variational Autoencoders (VAEs) to learn disentangled representations has made them popular for practical applications. However, their behaviour is not yet fully understood. For example, the questions of when they can provide…

机器学习 · 计算机科学 2022-09-27 Lisa Bonheme , Marek Grzes

As one of the most popular generative models, Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. However, when the decoder network is sufficiently expressive, VAE may lead…

机器学习 · 计算机科学 2021-10-26 Dazhong Shen , Chuan Qin , Chao Wang , Hengshu Zhu , Enhong Chen , Hui Xiong