Papers
Thu 25 Mar 2021
169 papers
- Nearly Horizon-Free Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Adversarial Imitation Learning with Trajectorial Augmentation and CorrectionOffline RL and imitation learning from data → Imitation learning methods
- Risk Bounds and Rademacher Complexity in Batch Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Hierarchical Program-Triggered Reinforcement Learning Agents For Automated DrivingEnd-to-end autonomous driving → Reinforcement learning for driving
- Self-Imitation Learning by PlanningOffline RL and imitation learning from data → Robot manipulation imitation learning
- Spirit Distillation: Precise Real-time Semantic Segmentation of Road Scenes with Insufficient DataKnowledge distillation → Detection and dense prediction distillation
- Bayesian Disturbance Injection: Robust Imitation Learning of Flexible PoliciesOffline RL and imitation learning from data → Imitation learning methods
- K-XLNet: A General Method for Combining Explicit Knowledge with Language Model Pretraining
- Looking into Your Speech: Learning Cross-modal Affinity for Audio-visual Speech Separation
- Weakly-supervised Audio-visual Sound Source Detection and Separation
- Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design
- Prototype-based Personalized Pruning
- Deep-AIR: A Hybrid CNN-LSTM Framework for Air Quality Modeling in Metropolitan Cities
- Classification of Pneumonia and Tuberculosis from Chest X-rays
- User-Oriented Smart General AI System under Causal Inference
- Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation
- Copolymer Informatics with Multi-Task Deep Neural Networks
- Deep-RBF Networks for Anomaly Detection in Automotive Cyber-Physical Systems
- COTR: Correspondence Transformer for Matching Across Images
- Few-shot Weakly-Supervised Object Detection via Directional Statistics
- Deep EHR Spotlight: a Framework and Mechanism to Highlight Events in Electronic Health Records for Explainable Predictions
- InversionNet3D: Efficient and Scalable Learning for 3D Full Waveform Inversion
- Residual Energy-Based Models for End-to-End Speech Recognition
- Equivariant Point Network for 3D Point Cloud Analysis
- Describing and Localizing Multiple Changes with Transformers
- Optimized Coverage Planning for UV Surface Disinfection
- Self-Labeling of Fully Mediating Representations by Graph Alignment
- Persistence Homology of TEDtalk: Do Sentence Embeddings Have a Topological Shape?
- Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes
- Negative Feedback System as Optimizer for Machine Learning Systems
- GPRAR: Graph Convolutional Network based Pose Reconstruction and Action Recognition for Human Trajectory Prediction
- Robust Data-Driven Predictive Control using Reachability Analysis
- The Geometry of Over-parameterized Regression and Adversarial Perturbations
- Stepwise Goal-Driven Networks for Trajectory Prediction
- Discriminative Semantic Transitive Consistency for Cross-Modal Learning
- Characterizing and Detecting Mismatch in Machine-Learning-Enabled Systems
- Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles
- Learning Stable Representations with Full Encoder
- Learning landmark geodesics using Kalman ensembles
- Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation
- Beyond permutation equivariance in graph networks
- Quantitative Prediction on the Enantioselectivity of Multiple Chiral Iodoarene Scaffolds Based on Whole Geometry
- A Meta-Reinforcement Learning Approach to Process Control
- Reinforcement Learning for Deceiving Reactive Jammers in Wireless Networks
- Tilted Cross Entropy (TCE): Promoting Fairness in Semantic Segmentation
- Realistic Differentially-Private Transmission Power Flow Data Release
- High-Fidelity Pluralistic Image Completion with Transformers
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
- Causal Inference Under Unmeasured Confounding With Negative Controls: A Minimax Learning Approach
- USB: Universal-Scale Object Detection Benchmark
- AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks
- The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI
- PlenOctrees for Real-time Rendering of Neural Radiance Fields
- AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting
- Orthogonal Projection Loss
- Scaling-up Disentanglement for Image Translation
- Zero-shot super-resolution with a physically-motivated downsampling kernel for endomicroscopy
- Self-Supervised Training Enhances Online Continual Learning
- Enabling Incremental Training with Forward Pass for Edge Devices
- Designing a Practical Degradation Model for Deep Blind Image Super-Resolution
- Contrasting Contrastive Self-Supervised Representation Learning Pipelines
- Rethinking Deep Contrastive Learning with Embedding Memory
- GridDehazeNet+: An Enhanced Multi-Scale Network with Intra-Task Knowledge Transfer for Single Image Dehazing
- Real-time low-resource phoneme recognition on edge devices
- More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval
- Adversarial Attacks on Deep Learning Based mmWave Beam Prediction in 5G and Beyond
- Learning Temporal Quantum Tomography
- Multi-Target Domain Adaptation via Unsupervised Domain Classification for Weather Invariant Object Detection
- Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation
- Visual Grounding Strategies for Text-Only Natural Language Processing
- SMILE: Self-Distilled MIxup for Efficient Transfer LEarning
- Recovering Quantitative Models of Human Information Processing with Differentiable Architecture Search
- Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark
- Multinomial Logit Contextual Bandits: Provable Optimality and Practicality
- Computational Mechanism for the Effect of Psychosis Community Treatment: A Conceptual Review from Neurobiology to Social Interaction
- ScanGAN360: A Generative Model of Realistic Scanpaths for 360circ Images
- Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification
- An Image is Worth 16x16 Words, What is a Video Worth?
- Regularization by Denoising Sub-sampled Newton Method for Spectral CT Multi-Material Decomposition
- About exchanging expectation and supremum for conditional Wasserstein GANs
- StyleLess layer: Improving robustness for real-world driving
- Measure Theoretic Weighted Model Integration
- Boosting Binary Masks for Multi-Domain Learning through Affine Transformations
- Finding Geometric Models by Clustering in the Consensus Space
- Inferring Latent Domains for Unsupervised Deep Domain Adaptation
- Transform consistency for learning with noisy labels
- Equality before the Law: Legal Judgment Consistency Analysis for Fairness
- A Retail Product Categorisation Dataset
- Active Inference Tree Search in Large POMDPs
- Group-CAM: Group Score-Weighted Visual Explanations for Deep Convolutional Networks
- Generative-Adversarial-Networks-based Ghost Recognition
- Searching for waveforms on spatially-filtered epileptic ECoG
- Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition
- Autism Spectrum Disorder Screening Using Discriminative Brain Sub-Networks: An Entropic Approach
- OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations
- Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning
- Universal Representation Learning from Multiple Domains for Few-shot Classification
- Deep Learning with robustness to missing data: A novel approach to the detection of COVID-19
- 3D3L: Deep Learned 3D Keypoint Detection and Description for LiDARs
- Model Order Reduction based on Runge-Kutta Neural Network
All 169
- Bertinho: Galician BERT Representations
- Improving Playtesting Coverage via Curiosity Driven Reinforcement Learning Agents
- Active Structure Learning of Bayesian Networks in an Observational Setting
- Interpretable Approximation of High-Dimensional Data
- Multi-frame Super-resolution from Noisy Data
- Patch Craft: Video Denoising by Deep Modeling and Patch Matching
- I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors
- Estimating Koopman operators for nonlinear dynamical systems: a nonparametric approach
- Data Augmentation with Variational Autoencoders and Manifold Sampling
- Video Instance Segmentation with a Propose-Reduce Paradigm
- KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs
- ECG-TCN: Wearable Cardiac Arrhythmia Detection with a Temporal Convolutional Network
- Deep Similarity Learning for Sports Team Ranking
- Variational Autoencoder-Based Vehicle Trajectory Prediction with an Interpretable Latent Space
- GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning
- AttrLostGAN: Attribute Controlled Image Synthesis from Reconfigurable Layout and Style
- Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting
- Spatial-spectral Hyperspectral Image Classification via Multiple Random Anchor Graphs Ensemble Learning
- ECINN: Efficient Counterfactuals from Invertible Neural Networks
- SSLayout360: Semi-Supervised Indoor Layout Estimation from 360-Degree Panorama
- On the Complexity of Learning Description Logic Ontologies
- MCTSteg: A Monte Carlo Tree Search-based Reinforcement Learning Framework for Universal Non-additive Steganography
- Robust subgroup discovery
- MBA-VO: Motion Blur Aware Visual Odometry
- Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation
- Explainability Guided Multi-Site COVID-19 CT Classification
- JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution
- Frame-rate Up-conversion Detection Based on Convolutional Neural Network for Learning Spatiotemporal Features
- Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation
- Structured Deep Kernel Networks for Data-Driven Closure Terms of Turbulent Flows
- Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
- Asymmetric CNN for image super-resolution
- A Survey of Quantization Methods for Efficient Neural Network Inference
- Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
- HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks
- Contextual Information Enhanced Convolutional Neural Networks for Retinal Vessel Segmentation in Color Fundus Images
- SubSpectral Normalization for Neural Audio Data Processing
- Gaussian Guided IoU: A Better Metric for Balanced Learning on Object Detection
- THAT: Two Head Adversarial Training for Improving Robustness at Scale
- An Approach to Improve Robustness of NLP Systems against ASR Errors
- Exploiting Class Similarity for Machine Learning with Confidence Labels and Projective Loss Functions
- Predicting Directionality in Causal Relations in Text
- Recent Advances in Large Margin Learning
- Mask Attention Networks: Rethinking and Strengthen Transformer
- Engineering an Intelligent Essay Scoring and Feedback System: An Experience Report
- Artificial Intelligence in Tumor Subregion Analysis Based on Medical Imaging: A Review
- Improving Online Forums Summarization via Hierarchical Unified Deep Neural Network
- BERT4SO: Neural Sentence Ordering by Fine-tuning BERT
- Learning Dynamic Alignment via Meta-filter for Few-shot Learning
- EfficientTDNN: Efficient Architecture Search for Speaker Recognition
- STA-VPR: Spatio-temporal Alignment for Visual Place Recognition
- On the Convexity of Discrete Time Covariance Steering in Stochastic Linear Systems with Wasserstein Terminal Cost
- Test-Time Training for Deformable Multi-Scale Image Registration
- MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation
- Approximating Instance-Dependent Noise via Instance-Confidence Embedding
- Deepfake Forensics via An Adversarial Game
- Jointly Modeling Heterogeneous Student Behaviors and Interactions Among Multiple Prediction Tasks
- On Evolving Attention Towards Domain Adaptation
- Rethinking Self-Supervised Learning: Small is Beautiful
- Efficient Feature Transformations for Discriminative and Generative Continual Learning
- Task-Oriented Low-Dose CT Image Denoising
- Prediction in the presence of response-dependent missing labels
- Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents
- Term-community-based topic detection with variable resolution
- An evidential classifier based on Dempster-Shafer theory and deep learning
- Benchmarking Modern Named Entity Recognition Techniques for Free-text Health Record De-identification
- Evidential fully convolutional network for semantic segmentation
- Hierarchical Proxy-based Loss for Deep Metric Learning
- Symmetry-Preserving Paths in Integrated Gradients