Neural Discrete Representation Learning
arXiv:1711.00937
Abstract
Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector Quantised-Variational AutoEncoder (VQ-VAE), differs from VAEs in two key ways: the encoder network outputs discrete, rather than continuous, codes; and the prior is learnt rather than static. In order to learn a discrete latent representation, we incorporate ideas from vector quantisation (VQ). Using the VQ method allows the model to circumvent issues of "posterior collapse" -- where the latents are ignored when they are paired with a powerful autoregressive decoder -- typically observed in the VAE framework. Pairing these representations with an autoregressive prior, the model can generate high quality images, videos, and speech as well as doing high quality speaker conversion and unsupervised learning of phonemes, providing further evidence of the utility of the learnt representations.
Cited by in corpus (429)
- A Survey on Visual Transformer
- On the Opportunities and Risks of Foundation Models
- Diffusion Models Beat GANs on Image Synthesis
- Diffusion Models in Vision: A Survey
- Zero-Shot Text-to-Image Generation
- Self-supervised Learning: Generative or Contrastive
- BEiT: BERT Pre-Training of Image Transformers
- Blended Diffusion for Text-driven Editing of Natural Images
- Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
- Cascaded Diffusion Models for High Fidelity Image Generation
- Model-Based Reinforcement Learning for Atari
- CogView: Mastering Text-to-Image Generation via Transformers
- Large Scale Adversarial Representation Learning
- Recent Advances in Autoencoder-Based Representation Learning
- vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations
- Uncertainty Estimation Using a Single Deep Deterministic Neural Network
- Neural Image Compression for Gigapixel Histopathology Image Analysis
- Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron
- Unsupervised speech representation learning using WaveNet autoencoders
- Leveraging Frequency Analysis for Deep Fake Image Recognition
- Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
- Masked Autoencoders Are Scalable Vision Learners
- Dynamical Variational Autoencoders: A Comprehensive Review
- EfficientFi: Towards Large-Scale Lightweight WiFi Sensing via CSI Compression
- SpaText: Spatio-Textual Representation for Controllable Image Generation
- Scaling Laws for Autoregressive Generative Modeling
- VideoGPT: Video Generation using VQ-VAE and Transformers
- Plan-Structured Deep Neural Network Models for Query Performance Prediction
- DiffWave: A Versatile Diffusion Model for Audio Synthesis
- Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
- Low Bit-Rate Speech Coding with VQ-VAE and a WaveNet Decoder
- Generative AI for Synthetic Data Across Multiple Medical Modalities: A Systematic Review of Recent Developments and Challenges
- MelNet: A Generative Model for Audio in the Frequency Domain
- Jukebox: A Generative Model for Music
- Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey
- Generating Diverse High-Fidelity Images with VQ-VAE-2
- From Variational to Deterministic Autoencoders
- Time Series Diffusion Method: A Denoising Diffusion Probabilistic Model for Vibration Signal Generation
- Face Generation and Editing with StyleGAN: A Survey
- Learning Disentangled Representations in the Imaging Domain
- Effectiveness of self-supervised pre-training for speech recognition
- CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders
- Vector-quantized Image Modeling with Improved VQGAN
- VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling
- Diagnosing and Enhancing VAE Models
- Towards a universal neural network encoder for time series
- Adaptive Latent Diffusion Model for 3D Medical Image to Image Translation: Multi-modal Magnetic Resonance Imaging Study
- Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging
- A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions
- GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions
- Bayesian Layers: A Module for Neural Network Uncertainty
- AudioDec: An Open-source Streaming High-fidelity Neural Audio Codec
- LDMVFI: Video Frame Interpolation with Latent Diffusion Models
- Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models
- Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends
- DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization
- LMQFormer: A Laplace-Prior-Guided Mask Query Transformer for Lightweight Snow Removal
- Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks
- Improving Inference for Neural Image Compression
- Lossy Image Compression with Quantized Hierarchical VAEs
- Context Disentangling and Prototype Inheriting for Robust Visual Grounding
- ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis
- Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis
- SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training
- Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion
- M6: A Chinese Multimodal Pretrainer
- StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks
- Unsupervised Paraphrase Generation using Pre-trained Language Models
- Explainable Time Series Anomaly Detection using Masked Latent Generative Modeling
- Artificial intelligence approaches for materials-by-design of energetic materials: state-of-the-art, challenges, and future directions
- Container: Context Aggregation Network
- Robust Training of Vector Quantized Bottleneck Models
- A Universal Music Translation Network
- Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniques
- Vector Quantized Diffusion Model for Text-to-Image Synthesis
- Learning from Few Samples: A Survey
- DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation
- Online Learned Continual Compression with Adaptive Quantization Modules
- LAFITE: Towards Language-Free Training for Text-to-Image Generation
- RockGPT: Reconstructing three-dimensional digital rocks from single two-dimensional slice from the perspective of video generation
- Avoiding Latent Variable Collapse With Generative Skip Models
- Audio Transformers
- Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion
- A Tutorial on Deep Latent Variable Models of Natural Language
- MatFuse: Controllable Material Generation with Diffusion Models
- PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers
- Latent Diffusion Model for Conditional Reservoir Facies Generation
- Autoregressive Quantile Networks for Generative Modeling
- Efficient automatic design of robots
- Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding
- Self-Supervised VQ-VAE for One-Shot Music Style Transfer
- CCVS: Context-aware Controllable Video Synthesis
- Feature Quantization Improves GAN Training
- Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models
- Parrot: Data-Driven Behavioral Priors for Reinforcement Learning
- ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design
- An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning
- Scalable and Efficient Neural Speech Coding: A Hybrid Design
- Hierarchical Quantized Autoencoders
- Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning
- Predicting Video with VQVAE
- X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers
- Hierarchical Autoregressive Image Models with Auxiliary Decoders
- Latent-Domain Predictive Neural Speech Coding
- Codified audio language modeling learns useful representations for music information retrieval
- Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation
- Poincaré Wasserstein Autoencoder
- An Empirical Study of Training End-to-End Vision-and-Language Transformers
- Differentiable JPEG: The Devil is in the Details
- Learning Latent Plans from Play
- Self-Supervised Learning with Kernel Dependence Maximization
- DiscreTalk: Text-to-Speech as a Machine Translation Problem
- Exploiting Negative Preference in Content-based Music Recommendation with Contrastive Learning
- TGAVC: Improving Autoencoder Voice Conversion with Text-Guided and Adversarial Training
- A multimodal dynamical variational autoencoder for audiovisual speech representation learning
- Taming Visually Guided Sound Generation
- MALA: Cross-Domain Dialogue Generation with Action Learning
- Aligned Contrastive Predictive Coding
- On the Convergence of AdaBound and its Connection to SGD
- A Survey on Self-supervised Pre-training for Sequential Transfer Learning in Neural Networks
- Generative Latent Flow
- A RAD approach to deep mixture models
- UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons
- Text-Free Prosody-Aware Generative Spoken Language Modeling
- A Review of Learning with Deep Generative Models from Perspective of Graphical Modeling
- Super-Resolving Face Image by Facial Parsing Information
- A Tandem Learning Rule for Effective Training and Rapid Inference of Deep Spiking Neural Networks
- Motif-Driven Contrastive Learning of Graph Representations
- VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net architecture
- VARA-TTS: Non-Autoregressive Text-to-Speech Synthesis based on Very Deep VAE with Residual Attention
- SimMIM: A Simple Framework for Masked Image Modeling
- Brain2Word: Decoding Brain Activity for Language Generation
- A Tutorial on VAEs: From Bayes' Rule to Lossless Compression
- Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills
- Associative Compression Networks for Representation Learning
- Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks
- Novelty Detection Via Blurring
- Non-Parallel Voice Conversion with Cyclic Variational Autoencoder
- Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations
- Prototype-based Neural Network Layers: Incorporating Vector Quantization
- Discrete-Valued Neural Communication
- Preventing Posterior Collapse with delta-VAEs
- Maximizing Mutual Information for Tacotron
- Multi-Instrumentalist Net: Unsupervised Generation of Music from Body Movements
- Neuromorphologicaly-preserving Volumetric data encoding using VQ-VAE
- Competitive Training of Mixtures of Independent Deep Generative Models
- 3D Brain and Heart Volume Generative Models: A Survey
- Score-based Generative Modeling in Latent Space
- Tiny Transformers for Environmental Sound Classification at the Edge
- Learning to Hash with Graph Neural Networks for Recommender Systems
- VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019
- Transformers predicting the future. Applying attention in next-frame and time series forecasting
- Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech
- Bayesian Image Reconstruction using Deep Generative Models
- Implicit Rank-Minimizing Autoencoder
- VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization
- Adversarial Feature Learning and Unsupervised Clustering based Speech Synthesis for Found Data with Acoustic and Textual Noise
- Vector Quantized Contrastive Predictive Coding for Template-based Music Generation
- Residual Correction in Real-Time Traffic Forecasting
- Variable-rate discrete representation learning
- Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE
- Source Separation with Deep Generative Priors
- Discrete Representations Strengthen Vision Transformer Robustness
- Interpretable agent communication from scratch (with a generic visual processor emerging on the side)
- VoiceGrad: Non-Parallel Any-to-Many Voice Conversion with Annealed Langevin Dynamics
- Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks
- Generating Images with Sparse Representations
- A vector quantized masked autoencoder for audiovisual speech emotion recognition
- COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations
- Autoencoding sensory substitution
- High Fidelity Face Manipulation with Extreme Poses and Expressions
- Variational Autoencoders with Riemannian Brownian Motion Priors
- A Contrastive Learning Approach for Training Variational Autoencoder Priors
- 3D-RETR: End-to-End Single and Multi-View 3D Reconstruction with Transformers
- Exploring TTS without T Using Biologically/Psychologically Motivated Neural Network Modules (ZeroSpeech 2020)
- Regularized Autoencoders via Relaxed Injective Probability Flow
- Information Maximizing Visual Question Generation
- (Self-Attentive) Autoencoder-based Universal Language Representation for Machine Translation
- Variational Variance: Simple, Reliable, Calibrated Heteroscedastic Noise Variance Parameterization
- SingSong: Generating musical accompaniments from singing
- FastS2S-VC: Streaming Non-Autoregressive Sequence-to-Sequence Voice Conversion
- Disentangling and Learning Robust Representations with Natural Clustering
- VQ-NeRF: Neural Reflectance Decomposition and Editing with Vector Quantization
- Learning Discrete Structured Representations by Adversarially Maximizing Mutual Information
- Video-Text Pre-training with Learned Regions
- Predictive Sampling with Forecasting Autoregressive Models
- Video-Guided Curriculum Learning for Spoken Video Grounding
- Gaussian mixture models with Wasserstein distance
- Locally Masked Convolution for Autoregressive Models
- Soft then Hard: Rethinking the Quantization in Neural Image Compression
- Weakly Supervised Disentangled Representation for Goal-conditioned Reinforcement Learning
- Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings
- Discovering Dialog Structure Graph for Open-Domain Dialog Generation
- Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Case
- Anytime Sampling for Autoregressive Models via Ordered Autoencoding
- Vector-Quantized Autoregressive Predictive Coding
- Attention Approximates Sparse Distributed Memory
- Variational Autoencoders for Jet Simulation
- Continuous Mixtures of Tractable Probabilistic Models
- MFCCGAN: A Novel MFCC-Based Speech Synthesizer Using Adversarial Learning
- Communication-Computation Trade-Off in Resource-Constrained Edge Inference
- Variational Inference In Pachinko Allocation Machines
- NoiseVC: Towards High Quality Zero-Shot Voice Conversion
- OCTOPUS: Overcoming Performance andPrivatization Bottlenecks in Distributed Learning
- Variational Autoencoder with Implicit Optimal Priors
- Unsupervised Paraphrasing by Simulated Annealing
- tvGP-VAE: Tensor-variate Gaussian Process Prior Variational Autoencoder
- Transfer Learning with Jukebox for Music Source Separation
- DanceAnyWay: Synthesizing Beat-Guided 3D Dances with Randomized Temporal Contrastive Learning
- CMTS: Conditional Multiple Trajectory Synthesizer for Generating Safety-critical Driving Scenarios
- Generative Models for Improved Naturalness, Intelligibility, and Voicing of Whispered Speech
- On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework
- Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes
- Vector-Quantized Timbre Representation
- Max-Affine Spline Insights into Deep Generative Networks
- Spatial PixelCNN: Generating Images from Patches
- Manifolds for Unsupervised Visual Anomaly Detection
- Spectrogram Inpainting for Interactive Generation of Instrument Sounds
- A survey on Variational Autoencoders from a GreenAI perspective
- A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery
- A Brief Overview of Unsupervised Neural Speech Representation Learning
- An Exploratory Study on Perceptual Spaces of the Singing Voice
- Deep Auto-encoder with Neural Response
- StarGAN-VC+ASR: StarGAN-based Non-Parallel Voice Conversion Regularized by Automatic Speech Recognition
- Latent Programmer: Discrete Latent Codes for Program Synthesis
- Unsupervised Subword Modeling Using Autoregressive Pretraining and Cross-Lingual Phone-Aware Modeling
- Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks
- Variational Inference for Data-Efficient Model Learning in POMDPs
- Select and Attend: Towards Controllable Content Selection in Text Generation
- fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit
- Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards
- Sliced Iterative Normalizing Flows
- Unsupervised Audiovisual Synthesis via Exemplar Autoencoders
- P-Hologen: An End-to-End Generative Framework for Phase-Only Holograms
- Target-Embedding Autoencoders for Supervised Representation Learning
- Self-supervised Tumor Segmentation through Layer Decomposition
- Modulating human brain responses via optimal natural image selection and synthetic image generation
- Entropy Minimization In Emergent Languages
- Extractive Summary as Discrete Latent Variables
- AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization
- FastVC: Fast Voice Conversion with non-parallel data
- Direct Evolutionary Optimization of Variational Autoencoders With Binary Latents
- Learning Latent Space Energy-Based Prior Model
- Training-free Subject-Enhanced Attention Guidance for Compositional Text-to-image Generation
- HAVANA: Hierarchical and Variation-Normalized Autoencoder for Person Re-identification
- Compositional Fine-Grained Low-Shot Learning
- UWSpeech: Speech to Speech Translation for Unwritten Languages
- Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes
- Deep Retrieval: Learning A Retrievable Structure for Large-Scale Recommendations
- VQ-DRAW: A Sequential Discrete VAE
- M3D-GAN: Multi-Modal Multi-Domain Translation with Universal Attention
- Neural-Symbolic Descriptive Action Model from Images: The Search for STRIPS
- Discond-VAE: Disentangling Continuous Factors from the Discrete
- CVC: Contrastive Learning for Non-parallel Voice Conversion
- Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders
- Unpaired Image-to-Image Translation via Latent Energy Transport
- Dueling Decoders: Regularizing Variational Autoencoder Latent Spaces
- Defending Against Image Corruptions Through Adversarial Augmentations
- High-Resolution Complex Scene Synthesis with Transformers
- Fast and Scalable Image Search For Histology
- Improved Transformer for High-Resolution GANs
- Image-Text Out-Of-Context Detection Using Synthetic Multimodal Misinformation
- Variational Open-Domain Question Answering
- DeepFracture: A Generative Approach for Predicting Brittle Fractures with Neural Discrete Representation Learning
- GA-GAN: CT reconstruction from Biplanar DRRs using GAN with Guided Attention
- Speech-to-speech Translation between Untranscribed Unknown Languages
- Unsupervised Learning For Sequence-to-sequence Text-to-speech For Low-resource Languages
- SketchBetween: Video-to-Video Synthesis for Sprite Animation via Sketches
- Exponential Tilting of Generative Models: Improving Sample Quality by Training and Sampling from Latent Energy
- Improved Prosody from Learned F0 Codebook Representations for VQ-VAE Speech Waveform Reconstruction
- Infomax Neural Joint Source-Channel Coding via Adversarial Bit Flip
- The Multi-speaker Multi-style Voice Cloning Challenge 2021
- Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning
- Semantics-Aware Human Motion Generation from Audio Instructions
- One-Class SVM on siamese neural network latent space for Unsupervised Anomaly Detection on brain MRI White Matter Hyperintensities
- Unsupervised Multimodal Word Discovery based on Double Articulation Analysis with Co-occurrence cues
- NWT: Towards natural audio-to-video generation with representation learning
- Robust Representation Learning via Perceptual Similarity Metrics
- Non-Intrusive Binaural Speech Intelligibility Prediction from Discrete Latent Representations
- MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining
- Exploring Fluent Query Reformulations with Text-to-Text Transformers and Reinforcement Learning
- not-so-BigGAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution
- The ELBO of Variational Autoencoders Converges to a Sum of Three Entropies
- Optimal Variance Control of the Score Function Gradient Estimator for Importance Weighted Bounds
- Nonparallel Voice Conversion with Augmented Classifier Star Generative Adversarial Networks
- I'm Sorry for Your Loss: Spectrally-Based Audio Distances Are Bad at Pitch
- Hierarchical disentangled representation learning for singing voice conversion
- crank: An Open-Source Software for Nonparallel Voice Conversion Based on Vector-Quantized Variational Autoencoder
- Decomposing Normal and Abnormal Features of Medical Images into Discrete Latent Codes for Content-Based Image Retrieval
- Blur, Noise, and Compression Robust Generative Adversarial Networks
- A Short Note on Analyzing Sequence Complexity in Trajectory Prediction Benchmarks
- Semi-Supervised Hierarchical Drug Embedding in Hyperbolic Space
- Set Distribution Networks: a Generative Model for Sets of Images
- Towards Interlingua Neural Machine Translation
- Foveation for Segmentation of Ultra-High Resolution Images
- Learning Sampling in Financial Statement Audits using Vector Quantised Autoencoder Neural Networks
- Unsupervised Acoustic Unit Representation Learning for Voice Conversion using WaveNet Auto-encoders
- asya: Mindful verbal communication using deep learning
- Latent Space Optimal Transport for Generative Models
- Likelihood Assignment for Out-of-Distribution Inputs in Deep Generative Models is Sensitive to Prior Distribution Choice
- Learning Product Codebooks using Vector Quantized Autoencoders for Image Retrieval
- NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing
- Fast gradient-free activation maximization for neurons in spiking neural networks
- Incorporating Real-world Noisy Speech in Neural-network-based Speech Enhancement Systems
- Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding
- Bridging the ELBO and MMD
- Trainable Class Prototypes for Few-Shot Learning
- Latent Vector Recovery of Audio GANs
- Feedback Recurrent AutoEncoder
- Discrete Acoustic Space for an Efficient Sampling in Neural Text-To-Speech
- A Framework for Generative and Contrastive Learning of Audio Representations
- D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
- L-Verse: Bidirectional Generation Between Image and Text
- Neuro-Symbolic Representations for Video Captioning: A Case for Leveraging Inductive Biases for Vision and Language
- The Image Local Autoregressive Transformer
- Relaxed-Responsibility Hierarchical Discrete VAEs
- Incorporating Symbolic Sequential Modeling for Speech Enhancement
- Reliable Categorical Variational Inference with Mixture of Discrete Normalizing Flows
- Latent Sensor Fusion: Multimedia Learning of Physiological Signals for Resource-Constrained Devices
- Cauchy-Schwarz Regularized Autoencoder
- Reconstructing hadronically decaying tau leptons with a jet foundation model
- Neural Communication Systems with Bandwidth-limited Channel
- Learning to Generate 3D Shapes with Generative Cellular Automata
- AE-OT-GAN: Training GANs from data specific latent distribution
- Unsupervised Disentanglement of Linear-Encoded Facial Semantics
- HRINet: Alternative Supervision Network for High-resolution CT image Interpolation
- Direct Noisy Speech Modeling for Noisy-to-Noisy Voice Conversion
- No Representation without Transformation
- MaskAAE: Latent space optimization for Adversarial Auto-Encoders
- Unsupervised Source Separation via Bayesian Inference in the Latent Domain
- A Factorial Mixture Prior for Compositional Deep Generative Models
- Many-to-Many Voice Conversion using Cycle-Consistent Variational Autoencoder with Multiple Decoders
- Discrete Few-Shot Learning for Pan Privacy
- Density Deconvolution with Normalizing Flows
- Generative networks as inverse problems with fractional wavelet scattering networks
- Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning
- Synthesising Activity Participations and Scheduling with Deep Generative Machine Learning
- Disentanglement of Latent Representations via Causal Interventions
- Hierarchical Timbre-Painting and Articulation Generation
- Generative Model without Prior Distribution Matching
- The Utility of Decorrelating Colour Spaces in Vector Quantised Variational Autoencoders
- Supervised Vector Quantized Variational Autoencoder for Learning Interpretable Global Representations
- Variational Learning for Unsupervised Knowledge Grounded Dialogs
- Exploring Disentanglement with Multilingual and Monolingual VQ-VAE
- Autoencoding Under Normalization Constraints
- Abstract Reasoning via Logic-guided Generation
- High Mutual Information in Representation Learning with Symmetric Variational Inference
- EdiBERT, a generative model for image editing
- Layered Controllable Video Generation
- CNN with large memory layers
- Synthesizing Photorealistic Images with Deep Generative Learning
- Synthetic weather radar using hybrid quantum-classical machine learning
- Measuring the Stability of Learned Features
- Irregular Convolutional Auto-Encoder on Point Clouds
- Discrete Variational Attention Models for Language Generation
- Complex-Valued Restricted Boltzmann Machine for Direct Speech Parameterization from Complex Spectra
- Exploration into Translation-Equivariant Image Quantization
- PocketVAE: A Two-step Model for Groove Generation and Control
- Semi-supervised Grasp Detection by Representation Learning in a Vector Quantized Latent Space
- PixelTransformer: Sample Conditioned Signal Generation
- Unsupervised Skill-Discovery and Skill-Learning in Minecraft
- Polyline Generative Navigable Space Segmentation for Autonomous Visual Navigation
- IB-DRR: Incremental Learning with Information-Back Discrete Representation Replay
- Learning Physical Concepts in Cyber-Physical Systems: A Case Study
- Depthwise Discrete Representation Learning
- Learning Interpretable and Discrete Representations with Adversarial Training for Unsupervised Text Classification
- Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings
- Entropy optimized semi-supervised decomposed vector-quantized variational autoencoder model based on transfer learning for multiclass text classification and generation
- Unsupervised Program Synthesis for Images By Sampling Without Replacement
- NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
- Introducing: DeepHead, Wide-band Electromagnetic Imaging Paradigm
- A New Framework for Machine Intelligence: Concepts and Prototype
- Symbolic Music Loop Generation with VQ-VAE
- Information Bottleneck Approach to Spatial Attention Learning
- Transformer VQ-VAE for Unsupervised Unit Discovery and Speech Synthesis: ZeroSpeech 2020 Challenge
- ScrewSense: Mapping the Invisible - Anomaly Detection and Error Classification in Screwdriving Processes
- Noise Robust Generative Adversarial Networks
- Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEncoder
- Supervised Encoding for Discrete Representation Learning
- Analysis of ODE2VAE with Examples
- Preliminary study on using vector quantization latent spaces for TTS/VC systems with consistent performance
- Voice Conversion Based Speaker Normalization for Acoustic Unit Discovery
- Comparative Snippet Generation
- Learned transform compression with optimized entropy encoding
- Lattice Representation Learning
- GIFnets: Differentiable GIF Encoding Framework
- Word Representation for Rhythms
- Learnable Triangulation for Deep Learning-based 3D Reconstruction of Objects of Arbitrary Topology from Single RGB Images
- Causal Representation Learning for Context-Aware Face Transfer
- Truth-Conditional Captioning of Time Series Data
- DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer
- Mutual Information Constraints for Monte-Carlo Objectives
- PatchGame: Learning to Signal Mid-level Patches in Referential Games
- OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
- Illiterate DALL-E Learns to Compose
- Quantization-Based Regularization for Autoencoders
- Efficient And Scalable Neural Residual Waveform Coding With Collaborative Quantization
- Zero-shot Voice Conversion via Self-supervised Prosody Representation Learning
- Variational latent discrete representation for time series modelling
- A Comparison of Discrete Latent Variable Models for Speech Representation Learning
- Learning Speaker Embedding from Text-to-Speech
- Applying the Information Bottleneck Principle to Prosodic Representation Learning
- Recent Advancements in Self-Supervised Paradigms for Visual Feature Representation
- Deep Sequence Learning for Video Anticipation: From Discrete and Deterministic to Continuous and Stochastic
- Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE
- Learning from Multiple Time Series: A Deep Disentangled Approach to Diversified Time Series Forecasting
- Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders
- Unified Signal Compression Using a GAN with Iterative Latent Representation Optimization
- Cross-modal Spectrum Transformation Network For Acoustic Scene classification
- Learning Disentangled Phone and Speaker Representations in a Semi-Supervised VQ-VAE Paradigm
- Discrete Auto-regressive Variational Attention Models for Text Modeling
- Learning the Imaging Landmarks: Unsupervised Key point Detection in Lung Ultrasound Videos
- Learning source-aware representations of music in a discrete latent space
- Testing for Typicality with Respect to an Ensemble of Learned Distributions
- Deep Conditional Measure Quantization
- Discrete representations in neural models of spoken language
- BandCondiNet: Parallel Transformers-based Conditional Popular Music Generation with Multi-View Features
- Inverse Graphics: Unsupervised Learning of 3D Shapes from Single Images
- End-To-End Dilated Variational Autoencoder with Bottleneck Discriminative Loss for Sound Morphing -- A Preliminary Study
- On the difficulty of a distributional semantics of spoken language
- A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion
- StreamHover: Livestream Transcript Summarization and Annotation
- Physics Driven Domain Specific Transporter Framework with Attention Mechanism for Ultrasound Imaging
- A Temporal Variational Model for Story Generation
- VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space
- A Generalised Linear Model Framework for -Variational Autoencoders based on Exponential Dispersion Families
- Computational principles of intelligence: learning and reasoning with neural networks
- Eccentric Regularization: Minimizing Hyperspherical Energy without explicit projection
- Differentiable Segmentation of Sequences