The paper interprets VQ-VAE loss as a form of information bottleneck.
problem Understanding the VQ-VAE loss function.
method Interpreted VQ-VAE loss as variational deterministic information bottleneck (VDIB) and variational information bottleneck (VIB).
result VQ-VAE loss can be derived from VDIB and approximated by VIB.
A new model trains prior and encoder/decoder networks simultaneously for efficient generation.
problem Complex autoregressive prior in VQ-VAE models leads to slow generation.
method Builds a diffusion bridge between continuous and non-informative prior distributions.
result Model is competitive and efficient in optimization and sampling.
New hierarchical VQ-VAE scheme improves image compression quality and features at low bitrates.
problem Low bitrate image compression maintaining quality and features.
method Hierarchical VQ-VAE with stochastic quantization and Markovian latent variables.
result High perceptual quality and semantic features at low bitrates.
S-VQ-VAE learns interpretable class-specific representations.
problem Learning interpretable representations of data.
method Supervised Vector Quantized Variational AutoEncoder (S-VQ-VAE).
result S-VQ-VAE learns interpretable class-specific representations.
Paper proposes a new Autoencoder for robustly encoding white matter streamlines.
problem Limited Autoencoder architectures ignore global streamline geometry and lack interpretability.
method Introduces Differentiable Vector Quantized Variational Autoencoder (D-VQ-VAE) for entire streamline bundles.
result Demonstrates superior performance in encoding and synthesis compared to state-of-the-art Autoencoders.
Enhanced VQ-VAE generates high-fidelity images faster.
problem Generating high-fidelity images efficiently.
method Scaled VQ-VAE with fast autoregressive sampling.
result VQ-VAE generates samples with quality rivaling GANs.
Improved vector quantization using Gaussian mixtures for better codebook utilization.
problem Training instability and information loss in discrete vector quantization.
method Generalized vector quantization with Gaussian mixture model and aggregated categorical posterior evidence lower bound.
result GM-VQ improves codebook utilization and reduces information loss without heuristics.
Unsupervised deep learning detects and localizes crop leaf diseases.
problem Automated detection and localization of crop diseases.
method Three types of autoencoders (CAE, CVAE, VQ-VAE) applied to an open-source dataset.
result VQ-VAE autoencoder outperforms in image reconstruction, anomaly removal, detection, and localization.
Paper presents a semi-supervised grasp detection method using VQ-VAE.
problem Robotic grasp detection difficulty due to insufficient labelled data.
method Semi-supervised learning with VQ-VAE in a latent space.
result Model performs better than existing approaches using unlabelled images.
New method for one-shot timbre transfer in music.
problem One-shot timbre transfer in music.
method Self-supervised VQ-VAE extension for disentangled representations.
result Outperforms selected baselines on objective metrics.
This paper introduces a quantization-based regularizer for autoencoders to improve latent representations.
problem Autoencoders can overfit and collapse, leading to poor latent representations.
method The authors combine VQ-VAE and denoising methods to introduce a bottleneck Bayesian estimator that soft quantizes latent codes.
result The method results in better latent representations for supervised and clustering tasks.
A new neural network model improves reinforcement learning efficiency.
problem Improving sample efficiency in reinforcement learning.
method Proposes a neural network architecture using VQ-VAE and convolutional LSTM for world modeling.
result Shows comparable performance to SimPLe with significantly smaller model.
Improved training for VQ-VAE models with robust codebook learning.
problem Challenges in training discrete latent variable models, especially VQ-VAEs.
method Increased learning rate and periodic re-initialization of codebook for robust training.
result More robust training and increased usage of latent codewords, even for large codebooks.
A new method learns discrete representations for images and videos, improving upon previous models.
problem Learning discrete representations for images and videos to improve performance.
method Depthwise application of Vector Quantized Variational Autoencoders (VQVAE) to feature axis.
result 33% improvement in performance compared to previous discrete models.
This work analyzes VQ-VAEs using information theory, focusing on latent variables and their impact on generalization and data generation.
problem Lack of theoretical analysis for latent variables in unsupervised models like VQ-VAEs.
method Information-theoretic analysis, introducing a novel data-dependent prior.
result Derives a generalization error bound for VQ-VAEs that depends on LV complexity and encoder, not decoder.
Enhances ocean floor mapping with adaptive uncertainty estimates.
problem Inaccurate bathymetric data for precise ocean modeling.
method Block-based conformal prediction with VQ-VAE architecture.
result Significant improvements in reconstruction quality and uncertainty estimation reliability.
Deep neural networks with discrete latent variables offer the promise of better symbolic reasoning, and learning abstractions that are more useful to new tasks. There has been a surge in interest in discrete latent variable models, however, despite several recent improvements, the training of discrete latent variable m…
Generative models struggle with class prediction on real data.
problem Evaluating generative models' ability to infer class labels.
method Trained classifiers on synthetic data generated by various models and tested on real data.
result Generative models from different classes outperform GANs on a new classification accuracy score (CAS).
Unsupervised learning of speech representations using WaveNet autoencoders.
problem Extract meaningful latent representations of speech signals.
method Applying autoencoding neural networks to speech waveforms, using a high capacity WaveNet decoder, and comparing three variants of latent representations.
result Comparable performance with top entries in the ZeroSpeech 2017 unsupervised acoustic unit discovery task.
Paper explores unsupervised learning for speech synthesis control.
problem Learning control over speech output without labeled data.
method Study of unsupervised training heuristics and autoencoder models.
result Unsupervised methods can be interpreted as variational inference.
The paper proposes a method to learn structured representations from unlabeled data using mutual information maximization.
problem Learning structured representations from unlabeled data.
method Adversarial maximization of mutual information between a structured latent variable and a target variable.
result The proposed method outperforms current baselines in document hashing and yields highly compressed interpretable representations.
Neural networks help auditors efficiently assess financial statements by learning underlying data patterns.
problem Efficiently auditing large volumes of financial statements and journal entries.
method Vector Quantised-Variational Autoencoder (VQ-VAE) neural networks.
result VQ-VAE neural networks can learn a quantized representation of accounting data, uncovering latent factors and providing a representative audit sample.
Quantized Variational Inference improves ELBO optimization with fast convergence.
problem Maximizing Evidence Lower Bound (ELBO) for variational inference.
method Optimal Voronoi Tesselation for variance-free gradients, Richardson extrapolation for asymptotic improvement.
result Quantized Variational Inference leads to fast convergence with comparable computational cost.
Neural network VQ-VAE with WaveNet decodes speech at 1.6 kbps with high quality.
problem Efficiently transmitting and storing speech signals at low bit-rates.
method VQ-VAE and WaveNet architecture for speech coding.
result Speech coding at 1.6 kbps with perceptual quality between MELP and AMR-WB.
A new algorithm for compressing latent representations in deep models.
problem Compressing continuous latent representations in deep models.
method Separates model design and training from quantization; uses adaptive quantization based on posterior uncertainty.
result Image compression with the proposed algorithm outperforms JPEG over a wide range of bit rates.
Generates high-quality images using sparse DCT representations.
problem Challenges in generating images due to high dimensionality.
method Transformers trained on sparse DCT block sequences.
result Competitive image generation quality with state-of-the-art methods.
Enhances speech quality in noisy environments using symbolic sequential modeling.
problem Improving speech quality in noisy conditions.
method Incorporates symbolic sequential modeling into speech enhancement framework.
result Significant improvement in speech quality metrics (PESQ, STOI) on TIMIT dataset.
The study explores the compressive power of Boolean threshold autoencoders, finding that seven layers are necessary but three are not.
problem Understanding the compressive limits of Boolean threshold autoencoders.
method Investigation into the minimum number of layers and nodes required for autoencoders to accurately transform binary vectors.
result There exists a seven-layer autoencoder with a logarithmic middle layer size for any set of distinct vectors, but not a three-layer one.
This research tackles automatic paraphrasing without translation.
problem Automatic paraphrasing without translation.
method Proposes a residual variant of vector-quantized variational auto-encoder trained on an unlabeled monolingual corpus.
result Monolingual paraphrasing outperforms unsupervised translation in all settings.
Jukebox generates high-fidelity songs with singing in raw audio.
problem Generating music with singing in raw audio.
method Multi-scale VQ-VAE for compression, autoregressive Transformers for modeling.
result Generates high-fidelity and diverse songs with coherence up to multiple minutes.
The autoencoder is an effective unsupervised learning model which is widely used in deep learning. It is well known that an autoencoder with a single fully-connected hidden layer, a linear activation function and a squared error cost function trains weights that span the same subspace as the one spanned by the principa…
Improved autoencoders guide latent sentence representations for better text generation and manipulation.
problem Current autoencoders struggle to maintain coherent latent spaces for meaningful text manipulations.
method Adversarial autoencoders with a denoising objective (DAAE) to guide latent space geometry.
result DAAE provides the best trade-off between generation quality and reconstruction capacity.
This paper explores autoencoders for estimating intrinsic dimensionality.
problem Estimating the intrinsic dimensionality of random vectors.
method Use of autoencoders for dimension estimation, focusing on architectural choices and regularization techniques.
result Autoencoders can be adapted for intrinsic dimension estimation, addressing questions beyond classic DR/DE techniques.
Method separates data into class and style factors using semi-supervised learning.
problem Separating generative factors of data into class and style vectors.
method Independent Vector Variational Autoencoders with semi-supervised learning and independence term.
result Improves classification performance and generation controllability.
SOM-VQ tokenizes discrete models with semantic structure and navigable topology.
problem Lack of semantic structure in vector quantized representations limits interpretable human control.
method Combines vector quantization with Self-Organizing Maps to learn discrete codebooks with explicit topology.
result SOM-VQ produces more learnable token sequences and provides an explicit navigable geometry in code space.
Novel fusion of autoencoders predicts sleepiness from speech.
problem Predicting sleepiness from speech recordings.
method Attention-based and recurrent sequence to sequence autoencoders for unsupervised representation learning.
result Fusion of autoencoders' representations achieves higher correlation with sleepiness scales.
We improve autoencoder image interpolation by shaping latent space.
problem Incongruities in autoencoder interpolation leading to artifacts or unrealistic results.
method Propose a regularization technique to shape latent space to follow a smooth, locally convex manifold consistent with training images.
result Faithful interpolation between data points achieved.
A new model designs molecular latent vectors for drug discovery.
problem Designing effective molecular descriptors from molecular structures.
method Proposes a denoising diffusion probabilistic model (DDPM) for variational autoencoding molecular graphs.
result Demonstrates superior prediction performance and robustness compared to existing approaches.
Enhances FAVAR models with autoencoder for better economic forecasting and interpretability.
problem Limitations of linear FAVAR models in forecasting and structural analysis.
method Introduces Grouped Sparse autoencoder with time-varying parameters.
result The Grouped Sparse autoencoder produces more interpretable factors and superior forecasting performance.
Recently, generative adversarial networks and adversarial autoencoders have gained a lot of attention in machine learning community due to their exceptional performance in tasks such as digit classification and face recognition. They map the autoencoder's bottleneck layer output (termed as code vectors) to different no…
The paper analyzes L2-regularized linear autoencoders and their loss landscapes.
problem Understanding the loss landscapes of L2-regularized linear autoencoders. method Smoothly parameterizing the critical manifold and relating minima to the MAP estimate of probabilistic PCA.
result Proves that L2-regularized LAEs learn principal directions as left singular vectors of the decoder. This paper proposes a novel type of random forests called a denoising random forests that are robust against noises contained in test samples. Such noise-corrupted samples cause serious damage to the estimation performances of random forests, since unexpected child nodes are often selected and the leaf nodes that the i…
Investigates latent variable models for useful generative concept representations.
problem Creating latent representations that support various concepts and attributes.
method Latent variable modeling, including latent variable models, latent representations, and latent spaces.
result Hierarchical latent representations and latent space vectors and geometry are effective for generative concept representations.
Unsupervised clustering is one of the most fundamental challenges in machine learning. A popular hypothesis is that data are generated from a union of low-dimensional nonlinear manifolds; thus an approach to clustering is identifying and separating these manifolds. In this paper, we present a novel approach to solve th…
A new framework reduces data upload for image classification while protecting user privacy.
problem Data upload limitations and privacy concerns in cloud-based image classification.
method Unsupervised autoencoder training at edge devices, followed by latent vector transmission to server for classifier training.
result The framework reduces communications overhead and protects user data privacy.
This paper reviews and benchmarks DVAEs for sequential data.
problem Processing sequential data with temporal dependencies.
method Dynamical Variational Autoencoders (DVAEs) for sequential data.
result Experimental benchmark on speech analysis-resynthesis task.
A deep learning method reduces chemometric data size and improves analysis accuracy.
problem The curse of dimensionality in chemometric data analysis.
method L2 regularized sparse autoencoder with automatic node selection and Gaussian process regression.
result Significant improvement in regression accuracy compared to state-of-the-art methods.
CGNP embeds functional processes into latent vectors using graph neural networks.
problem Embedding and sampling functional processes over arbitrary domains.
method CGNP employs graph neural networks to embed and decode functional processes.
result CGNP effectively samples encoded functions over any domain.