Papers
Tue 22 Jun 2021
180 papers
- Provably Efficient Representation Selection in Low-rank Markov Decision Processes: From Online to Offline RLOffline RL and imitation learning from data → Offline RL algorithms
- NuPlan: A closed-loop ML-based planning benchmark for autonomous vehiclesWorld models → World models for autonomous driving +1
- Differentiable Programming of Reaction-Diffusion Patterns
- Statistical Analysis of Perspective Scores on Hate Speech Detection
- Face Identification Proficiency Test Designed Using Item Response Theory
- Serial-EMD: Fast Empirical Mode Decomposition Method for Multi-dimensional Signals Based on Serialization
- Joint Learning of Portrait Intrinsic Decomposition and Relighting
- Multimodal Emergent Fake News Detection via Meta Neural Process Networks
- Bayesian Neural Networks: Essentials
- Towards Biologically Plausible Convolutional Networks
- Neural networks for dengue forecasting: a systematic review
- Recurrent Neural Network from Adder's Perspective: Carry-lookahead RNN
- Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Tasks
- DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?
- Diabetic Retinopathy Detection using Ensemble Machine Learning
- Fine-Tuning StyleGAN2 For Cartoon Face Generation
- Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers
- Regret-optimal Estimation and Control
- Learning Identity-Preserving Transformations on Data Manifolds
- BFTrainer: Low-Cost Training of Neural Networks on Unfillable Supercomputer Nodes
- Structured in Space, Randomized in Time: Leveraging Dropout in RNNs for Efficient Training
- A Federated Data-Driven Evolutionary Algorithm for Expensive Multi/Many-objective Optimization
- Forecasting Health and Wellbeing for Shift Workers Using Job-role Based Deep Neural Network
- Reachability Analysis of Convolutional Neural Networks
- Towards Consistent Predictive Confidence through Fitted Ensembles
- The Rate of Convergence of Variation-Constrained Deep Neural Networks
- It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning
- A Practical & Unified Notation for Information-Theoretic Quantities in ML
- Faster Randomized Methods for Orthogonality Constrained Problems
- Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning
- On Positivity Bias in Negative Reviews
- Automatic Head Overcoat Thickness Measure with NASNet-Large-Decoder Net
- Volume Rendering of Neural Implicit Surfaces
- Pure Exploration in Kernel and Neural Bandits
- A Simple and Practical Approach to Improve Misspellings in OCR Text
- ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences
- The Neurally-Guided Shape Parser: Grammar-based Labeling of 3D Shape Regions with Approximate Inference
- Q-Learning Lagrange Policies for Multi-Action Restless Bandits
- Team PyKale (xy9) Submission to the EPIC-Kitchens 2021 Unsupervised Domain Adaptation Challenge for Action Recognition
- On Matrix Factorizations in Subspace Clustering
- Transfer Learning of Deep Spatiotemporal Networks to Model Arbitrarily Long Videos of Seizures
- Test-time Collective Prediction
- P2T: Pyramid Pooling Transformer for Scene Understanding
- Exploring the Representational Power of Graph Autoencoder
- On the Diversity and Limits of Human Explanations
- Learned Interpretable Residual Extragradient ISTA for Sparse Coding
- Tracking Instances as Queries
- Variance-Aware Off-Policy Evaluation with Linear Function Approximation
- Revisiting Deep Learning Models for Tabular Data
- Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation
- Unsupervised Object-Level Representation Learning from Scene Images
- Fundamental limits for rank-one matrix estimation with groupwise heteroskedasticity
- MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images
- Reusing Combinatorial Structure: Faster Iterative Projections over Submodular Base Polytopes
- RootPainter3D: Interactive-machine-learning enables rapid and accurate contouring for radiotherapy
- Robust Regression Revisited: Acceleration and Improved Estimation Rates
- Sparsistent Model Discovery
- On the importance of cross-task features for class-incremental learning
- Joint Deep Reversible Regression Model and Physics-Informed Unsupervised Learning for Temperature Field Reconstruction
- Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection
- G-VAE, a Geometric Convolutional VAE for ProteinStructure Generation
- Enhanced Separable Disentanglement for Unsupervised Domain Adaptation
- Residual Networks as Flows of Velocity Fields for Diffeomorphic Time Series Alignment
- Dangers of Bayesian Model Averaging under Covariate Shift
- PALMAR: Towards Adaptive Multi-inhabitant Activity Recognition in Point-Cloud Technology
- Local policy search with Bayesian optimization
- A Latent Transformer for Disentangled Face Editing in Images and Videos
- Making Invisible Visible: Data-Driven Seismic Inversion with Spatio-temporally Constrained Data Augmentation
- On the Evaluation of Machine Translation for Terminology Consistency
- Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
- Notes on the H-measure of classifier performance
- Failing with Grace: Learning Neural Network Controllers that are Boundedly Unsafe
- Dynamic Customer Embeddings for Financial Service Applications
- Asynchronous Stochastic Optimization Robust to Arbitrary Delays
- Multiple Organ Failure Prediction with Classifier-Guided Generative Adversarial Imputation Networks
- Randomness In Neural Network Training: Characterizing The Impact of Tooling
- NetFense: Adversarial Defenses against Privacy Attacks on Neural Networks for Graph Data
- Towards Automated Evaluation of Explanations in Graph Neural Networks
- Graph coarsening: From scientific computing to machine learning
- MEAL: Manifold Embedding-based Active Learning
- HybVIO: Pushing the Limits of Real-time Visual-inertial Odometry
- Off-Policy Reinforcement Learning with Delayed Rewards
- Credal Self-Supervised Learning
- Stochastic Polyak Stepsize with a Moving Target
- Algorithmic Recourse in Partially and Fully Confounded Settings Through Bounding Counterfactual Effects
- Machine learning for risk assessment in gender-based crime
- Detecting Anomalous User Behavior in Remote Patient Monitoring
- Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval
- Speeding Up OPFython with Numba
- Lower and Upper Bounds on the VC-Dimension of Tensor Network Models
- A Clustering-based Framework for Classifying Data Streams
- Data Augmentation for Opcode Sequence Based Malware Detection
- User Identification across Social Networking Sites using User Profiles and Posting Patterns
- Enabling Long-Term Cooperation in Cross-Silo Federated Learning: A Repeated Game Perspective
- Evaluation of a Region Proposal Architecture for Multi-task Document Layout Analysis
- End-to-End Task-Oriented Dialog Modeling with Semi-Structured Knowledge Management
- Exemplars-guided Empathetic Response Generation Controlled by the Elements of Human Communication
- Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech
- Symplectic Learning for Hamiltonian Neural Networks
- LV-BERT: Exploiting Layer Variety for BERT
All 180
- Error-Aware Interactive Semantic Parsing of OpenStreetMap
- Lifted Model Checking for Relational MDPs
- FLEA: Provably Robust Fair Multisource Learning from Unreliable Training Data
- MIMIR: Deep Regression for Automated Analysis of UK Biobank Body MRI
- RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video
- Neural Distributed Image Compression using Common Information
- A Deep Latent Space Model for Graph Representation Learning
- Test Distribution-Aware Active Learning: A Principled Approach Against Distribution Shift and Outliers
- Learning Dynamical Systems from Noisy Sensor Measurements using Multiple Shooting
- Categorising Fine-to-Coarse Grained Misinformation: An Empirical Study of COVID-19 Infodemic
- The Hitchhiker's Guide to Prior-Shift Adaptation
- A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning
- Gradient-based Label Binning in Multi-label Classification
- DARTS-PRIME: Regularization and Scheduling Improve Constrained Optimization in Differentiable NAS
- A Curriculum-style Self-training Approach for Source-Free Semantic Segmentation
- MMD-MIX: Value Function Factorisation with Maximum Mean Discrepancy for Cooperative Multi-Agent Reinforcement Learning
- A Survey on Human-aware Robot Navigation
- NCIS: Neural Contextual Iterative Smoothing for Purifying Adversarial Perturbations
- Repulsive Deep Ensembles are Bayesian
- Confidence-Aware Learning for Camouflaged Object Detection
- Discovering Heterogeneous Treatment Effects in Regression Discontinuity Designs
- Machine Learning for Model Order Selection in MIMO OFDM Systems
- On Adversarial Robustness of Synthetic Code Generation
- Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition
- Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation
- Distributional Gradient Matching for Learning Uncertain Neural Dynamics Models
- Information Retrieval for ZeroSpeech 2021: The Submission by University of Wroclaw
- Multi-layered Semantic Representation Network for Multi-label Image Classification
- Reinforcement Learning for Physical Layer Communications
- A Vertical Federated Learning Framework for Graph Convolutional Network
- Part-Aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking
- A Comparison for Patch-level Classification of Deep Learning Methods on Transparent Environmental Microorganism Images: from Convolutional Neural Networks to Visual Transformers
- Continuous-Depth Neural Models for Dynamic Graph Prediction
- Solving Stochastic Optimization with Expectation Constraints Efficiently by a Stochastic Augmented Lagrangian-Type Algorithm
- Universal Domain Adaptation in Ordinal Regression
- Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering
- FLRA: A Reference Architecture for Federated Learning Systems
- SENT: Sentence-level Distant Relation Extraction via Negative Training
- Creating A New Color Space utilizing PSO and FCM to Perform Skin Detection by using Neural Network and ANFIS
- SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
- Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge
- Hand-Drawn Electrical Circuit Recognition using Object Detection and Node Recognition
- Learning-Based Practical Light Field Image Compression Using A Disparity-Aware Model
- Winning the CVPR'2021 Kinetics-GEBD Challenge: Contrastive Learning Approach
- Adaptive Learning Rate and Momentum for Training Deep Neural Networks
- Connection Sensitivity Matters for Training-free DARTS: From Architecture-Level Scoring to Operation-Level Sensitivity Analysis
- Kernel Clustering with Sigmoid-based Regularization for Efficient Segmentation of Sequential Data
- DocFormer: End-to-End Transformer for Document Understanding
- Deep3DPose: Realtime Reconstruction of Arbitrarily Posed Human Bodies from Single RGB Images
- Particle Cloud Generation with Message Passing Generative Adversarial Networks
- Do Language Models Perform Generalizable Commonsense Inference?
- Graph Routing between Capsules
- Recent Deep Semi-supervised Learning Approaches and Related Works
- BARTScore: Evaluating Generated Text as Text Generation
- Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations
- Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering
- SA-LOAM: Semantic-aided LiDAR SLAM with Loop Closure
- Rethinking Adam: A Twofold Exponential Moving Average Approach
- An Accurate Non-accelerometer-based PPG Motion Artifact Removal Technique using CycleGAN
- Knowing How to Plan
- Game-Theoretic Models of Moral and Other-Regarding Agents (extended abstract)
- Knowledge from Probability
- Are the Players in an Interactive Belief Model Meta-certain of the Model Itself?
- De Re Updates
- Collective Argumentation: The Case of Aggregating Support-Relations of Bipolar Argumentation Frameworks
- Routine Clustering of Mobile Sensor Data Facilitates Psychotic Relapse Prediction in Schizophrenia Patients
- Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification
- Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis
- A Comprehensive Comparison of Pre-training Language Models
- Wallpaper Texture Generation and Style Transfer Based on Multi-label Semantics
- SeqNetVLAD vs PointNetVLAD: Image Sequence vs 3D Point Clouds for Day-Night Place Recognition
- VoxelEmbed: 3D Instance Segmentation and Tracking with Voxel Embedding based Deep Learning
- Fourier Transform Approximation as an Auxiliary Task for Image Classification
- Sequential Late Fusion Technique for Multi-modal Sentiment Analysis
- Multimodal trajectory forecasting based on discrete heat map
- Gait analysis with curvature maps: A simulation study
- A Logical Neural Network Structure With More Direct Mapping From Logical Relations
- Querying in the Age of Graph Databases and Knowledge Graphs
- KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers
- A Competitive Analysis of Online Multi-Agent Path Finding