Bayes-Factor-VAE: Hierarchical Bayesian Deep Auto-Encoder Models for Factor Disentanglement

Kim, Minyoung; Wang, Yuting; Sahu, Pritish; Pavlović, Vladimir

doi:10.1109/iccv.2019.00307

Cited by 21 publications

(15 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this end, we apply a one-toone dependency structure to the observed variables and the latent code, as shown in Figure 4a. Beyond a visual, qualitative validation, we quantify the disentanglement capacity of our approach by using the dSprites dataset, following the setups of [Kim and Mnih, 2017]. The disentanglement scores calculated for InfoGAN and our approach across various IRs are reported in Figure 4b.…”

Section: Methodsmentioning

confidence: 99%

“…InfoGAN [Chen et al, 2016], where the mutual information between the observed and the extracted latent feature subsets are maximized to realize the disentanglement. In addition to a set of subsequent studies such as [Tran et al, 2017;Lee et al, 2020], we are aware of two recent works [Kim et al, 2019;Beyazit et al, 2020] that also respect dependency structure among variables in the latent space with Bayesian treatment. However, these works were to extract various types of salient features while our task is imbalanced classification.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Interpretable Minority Synthesis for Imbalanced Classification

Lin

Yuan

et al. 2021

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

This paper proposes a novel oversampling approach that strives to balance the class priors with a considerably imbalanced data distribution of high dimensionality. The crux of our approach lies in learning interpretable latent representations that can model the synthetic mechanism of the minority samples by using a generative adversarial network(GAN). A Bayesian regularizer is imposed to guide the GAN to extract a set of salient features that are either disentangled or intensionally entangled, with their interplay controlled by a prescribed structure, defined with human-in-the-loop. As such, our GAN enjoys an improved sample complexity, being able to synthesize high-quality minority samples even if the sizes of minority classes are extremely small during training. Empirical studies substantiate that our approach can empower simple classifiers to achieve superior imbalanced classification performance over the state-of-the-art competitors and is robust across various imbalance settings. Code is released in github.com/fudonglin/IMSIC.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Interpretable Minority Synthesis for Imbalanced Classification

Lin

Yuan

et al. 2021

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Neural 3D Point Cloud Generation. While 2D image generation has been widely investigated using GANS (Isola et al 2017;Zhu et al 2017) and VAES (Kingma and Welling 2014;Higgins et al 2016;Kim et al 2019b;Sohn, Lee, and Yan 2015), neural 3D point cloud generation has only been explored in recent years. Achlioptas et al (2018) first proposed the r-GAN to generate 3D point clouds, with fully connected layers as the generator.…”

Section: Related Workmentioning

confidence: 99%

EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation

Li¹,

Liu²,

Walder³

2021

Preprint

View full text Add to dashboard Cite

This paper tackles the problem of parts-aware point cloud generation. Unlike existing works which require the point cloud to be segmented into parts a priori, our parts-aware editing and generation is performed in an unsupervised manner. We achieve this with a simple modification of the Variational Auto-Encoder which yields a joint model of the point cloud itself along with a schematic representation of it as a combination of shape primitives. In particular, we introduce a latent representation of the point cloud which can be decomposed into a disentangled representation for each part of the shape. These parts are in turn disentangled into both a shape primitive and a point cloud representation, along with a standardising transformation to a canonical coordinate system. The dependencies between our standardising transformations preserve the spatial dependencies between the parts in a manner which allows meaningful parts-aware point cloud generation and shape editing. In addition to the flexibility afforded by our disentangled representation, the inductive bias introduced by our joint modelling approach yields the state-of-the-art experimental results on the ShapeNet dataset.

show abstract

“…Therefore, we additionally apply using long-tail distributions to model relevant factors, as the disentangled latent variables responsible for major sources of variability. Specifically, the VAE is extended to a hierarchical Bayesian model by introducing hyper-priors on the variances of Gaussian latent priors, while maintaining tractable learning and inference of the traditional VAEs [11]. For relevant factors, it is necessary to have p(z j ) different from N (0, 1).…”

Section: Representation With Improved Disentanglementmentioning

confidence: 99%

OIAD: One-for-all Image Anomaly Detection with Disentanglement Learning

Wang¹,

Chen

et al. 2020

Preprint

View full text Add to dashboard Cite

Anomaly detection aims to recognize samples with anomalous and unusual patterns with respect to a set of normal data. This is significant for numerous domain applications, such as industrial inspection, medical imaging, and security enforcement. There are two key research challenges associated with existing anomaly detection approaches: (1) many approaches perform well on low-dimensional problems however the performance on high-dimensional instances, such as images, is limited; (2) many approaches often rely on traditional supervised approaches and manual engineering of features, while the topic has not been fully explored yet using modern deep learning approaches, even when the well-label samples are limited. In this paper, we propose a One-for-all Image Anomaly Detection system (OIAD) based on disentangled learning using only clean samples. Our key insight is that the impact of small perturbation on the latent representation can be bounded for normal samples while anomaly images are usually outside such bounded intervals, referred to as structure consistency. We implement this idea and evaluate its performance for anomaly detection. Our experiments with three datasets show that OIAD can detect over 90% of anomalies while maintaining a low false alarm rate. It can also detect suspicious samples from samples labeled as clean, coincided with what humans would deem unusual.

show abstract

Bayes-Factor-VAE: Hierarchical Bayesian Deep Auto-Encoder Models for Factor Disentanglement

Cited by 21 publications

References 10 publications

Interpretable Minority Synthesis for Imbalanced Classification

Interpretable Minority Synthesis for Imbalanced Classification

EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation

OIAD: One-for-all Image Anomaly Detection with Disentanglement Learning

Contact Info

Product

Resources

About