Papers
Mon 8 Mar 2021
164 papers
- Domain-Robust Visual Imitation Learning with Mutual Information ConstraintsOffline RL and imitation learning from data → Imitation learning methods
- Deep Model Intellectual Property Protection via Deep WatermarkingLLM safety and security → Watermarking generated content and models
- Instabilities of Offline RL with Pre-Trained Neural RepresentationOffline RL and imitation learning from data → Offline RL algorithms
- Latent Imagination Facilitates Zero-Shot Transfer in Autonomous RacingWorld models → Latent dynamics models and model-based RL
- Parser-Free Virtual Try-on via Distilling Appearance FlowsKnowledge distillation → General knowledge distillation methods
- Split Computing and Early Exiting for Deep Learning Applications: Survey and Research ChallengesEfficient LLM inference and serving → Early exit and edge inference
- Compiler Toolchains for Deep Learning Workloads on Embedded Platforms
- Depth Evaluation for Metal Surface Defects by Eddy Current Testing using Deep Residual Convolutional Neural Networks
- Increasing Energy Efficiency of Massive-MIMO Network via Base Stations Switching using Reinforcement Learning and Radio Environment Maps
- Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do
- A Classical Search Game in Discrete Locations
- A Bayesian Multiscale Deep Learning Framework for Flows in Random Media
- Deep Transfer Learning for Infectious Disease Case Detection Using Electronic Medical Records
- Hypervector Design for Efficient Hyperdimensional Computing on Edge Devices
- ZYELL-NCTU NetTraffic-1.0: A Large-Scale Dataset for Real-World Network Anomaly Detection
- Multi-phase Deformable Registration for Time-dependent Abdominal Organ Variations
- Differentially Private Imaging via Latent Space Manipulation
- Contrastive Neural Architecture Search with Neural Architecture Comparators
- Formal Verification of Stochastic Systems with ReLU Neural Network Controllers
- Benchmarking Off-The-Shelf Solutions to Robotic Assembly Tasks
- On the Oracle Complexity of Higher-Order Smooth Non-Convex Finite-Sum Optimization
- Contemplating real-world object classification
- A Topological Approach to Compare Document Semantics Based on a New Variant of Syntactic N-grams
- Constrained Learning with Non-Convex Losses
- AfriVEC: Word Embedding Models for African Languages. Case Study of Fon and Nobiin
- Few-Shot Learning of an Interleaved Text Summarization Model by Pretraining with Synthetic Data
- Model Complexity of Deep Learning: A Survey
- Exact Distribution-Free Hypothesis Tests for the Regression Function of Binary Classification via Conditional Kernel Mean Embeddings
- Classification and Feature Transformation with Fuzzy Cognitive Maps
- Deep Transfer Learning for WiFi Localization
- Multiple Instance Captioning: Learning Representations from Histopathology Textbooks and Articles
- ASL to PET Translation by a Semi-supervised Residual-based Attention-guided Convolutional Neural Network
- CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection
- Forest Guided Smoothing
- Learning Connectivity for Data Distribution in Robot Teams
- How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Lines
- A Parallelizable Lattice Rescoring Strategy with Neural Language Models
- Offboard 3D Object Detection from Point Cloud Sequences
- Text Simplification by Tagging
- Domain Controlled Title Generation with Human Evaluation
- Bias-Corrected Peaks-Over-Threshold Estimation of the CVaR
- Nearest Neighbor Search Under Uncertainty
- LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAM
- Size-Invariant Graph Representations for Graph Classification Extrapolations
- Advances in Inference and Representation for Simultaneous Localization and Mapping
- Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning
- Program Synthesis Over Noisy Data with Guarantees
- Fast and Effective Biomedical Entity Linking Using a Dual Encoder
- Self-learning Machines based on Hamiltonian Echo Backpropagation
- A multi-agent reinforcement learning model of reputation and cooperation in human groups
- Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation
- F-CAD: A Framework to Explore Hardware Accelerators for Codec Avatar Decoding
- Learning to Represent and Predict Sets with Deep Neural Networks
- Automatic Cause Detection of Performance Problems in Web Applications
- A Comparative Approach to Explainable Artificial Intelligence Methods in Application to High-Dimensional Electronic Health Records: Examining the Usability of XAI
- Digital Beamforming Robust to Time-Varying Carrier Frequency Offset
- Approximate Bayesian inference and forecasting in huge-dimensional multi-country VARs
- InFillmore: Frame-Guided Language Generation with Bidirectional Context
- Monte Carlo Tree Search: A Review of Recent Modifications and Applications
- Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models
- A Survey of Embodied AI: From Simulators to Research Tasks
- Analysis of Convolutional Decoder for Image Caption Generation
- The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning
- Autonomous object harvesting using synchronized optoelectronic microrobots
- A Crash Course on Reinforcement Learning
- Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem
- Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networks
- Data-driven Cloud Clustering via a Rotationally Invariant Autoencoder
- Scale invariant robot behavior with fractals
- Empirical comparison between autoencoders and traditional dimensionality reduction methods
- The Weakly-Labeled Rand Index
- Domain Adaptive Egocentric Person Re-identification
- From Hand-Perspective Visual Information to Grasp Type Probabilities: Deep Learning via Ranking Labels
- Risk Aware Optimization of Water Sensor Placement
- Injecting Knowledge in Data-driven Vehicle Trajectory Predictors
- Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding
- Adversarial Reinforcement Learning for Procedural Content Generation
- Relationship-based Neural Baby Talk
- HANDS: A Multimodal Dataset for Modeling Towards Human Grasp Intent Inference in Prosthetic Hands
- Machine-learning based methodologies for 3d x-ray measurement, characterization and optimization for buried structures in advanced ic packages
- Deeply Unsupervised Patch Re-Identification for Pre-training Object Detectors
- Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization
- Reliability-Aware Quantization for Anti-Aging NPUs
- PyRCN: A Toolbox for Exploration and Application of Reservoir Computing Networks
- Detecting quantum entanglement with unsupervised learning
- Look, Cast and Mold: Learning 3D Shape Manifold from Single-view Synthetic Data
- Combining Interventional and Observational Data Using Causal Reductions
- DDGC: Generative Deep Dexterous Grasping in Clutter
- Bridging the Distribution Gap of Visible-Infrared Person Re-identification with Modality Batch Normalization
- A Study on Fairness and Trust Perceptions in Automated Decision Making
- Towards Human-Like Automated Test Generation: Perspectives from Cognition and Problem Solving
- Low-Rank Sinkhorn Factorization
- Content-Aware Detection of Temporal Metadata Manipulation
- Self-Augmented Multi-Modal Feature Embedding
- Efficient Algorithms for Finite Horizon and Streaming Restless Multi-Armed Bandit Problems
- Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning
- Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation
- Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie
- Cluster-based Input Weight Initialization for Echo State Networks
- Dual-Task Mutual Learning for Semi-Supervised Medical Image Segmentation
All 164
- A Taxonomy of Similarity Metrics for Markov Decision Processes
- Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation
- On Implicit Attribute Localization for Generalized Zero-Shot Learning
- Interpretable Attention Guided Network for Fine-grained Visual Classification
- Unsupervised Object-Based Transition Models for 3D Partially Observable Environments
- Semiotically-grounded distant viewing of diagrams: insights from two multimodal corpora
- Meta-Learning with MAML on Trees
- Reverse Differentiation via Predictive Coding
- A Novel Perspective for Positive-Unlabeled Learning via Noisy Labels
- Learning Graph Neural Networks with Positive and Unlabeled Nodes
- Time and Frequency Network for Human Action Detection in Videos
- Behavior-Driven Synthesis of Human Dynamics
- Distributed Reinforcement Learning for Flexible and Efficient UAV Swarm Control
- Anomaly Detection Based on Selection and Weighting in Latent Space
- You Only Learn Once: Universal Anatomical Landmark Detection
- FEDS -- Filtered Edit Distance Surrogate
- Personalized Federated Learning using Hypernetworks
- Consistency Regularization for Adversarial Robustness
- Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification
- Synplex: A synthetic simulator of highly multiplexed histological images
- Comparing Popular Simulation Environments in the Scope of Robotics and Reinforcement Learning
- Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
- Unified Batch All Triplet Loss for Visible-Infrared Person Re-identification
- CheXseen: Unseen Disease Detection for Deep Learning Interpretation of Chest X-rays
- Deep Gradient Projection Networks for Pan-sharpening
- Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering
- Testing Autonomous Systems with Believed Equivalence Refinement
- Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing
- MCR-Net: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension
- Improving Transformation-based Defenses against Adversarial Examples with First-order Perturbations
- Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization
- CRLF: Automatic Calibration and Refinement based on Line Feature for LiDAR and Camera in Road Scenes
- Asymptotics of Ridge Regression in Convolutional Models
- T-SCI: A Two-Stage Conformal Inference Algorithm with Guaranteed Coverage for Cox-MLP
- Real-world Ride-hailing Vehicle Repositioning using Deep Reinforcement Learning
- Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models
- U-DuDoNet: Unpaired dual-domain network for CT metal artifact reduction
- Behavior From the Void: Unsupervised Active Pre-Training
- No Weighted-Regret Learning in Adversarial Bandits with Delays
- Learning to Control an Unstable System with One Minute of Data: Leveraging Gaussian Process Differentiation in Predictive Control
- Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games
- Exploring a Makeup Support System for Transgender Passing based on Automatic Gender Recognition
- A Reinforcement Learning Based R-Tree for Spatial Data Indexing in Dynamic Environments
- Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games
- Multimodal Representation Learning via Maximization of Local Mutual Information
- Decision-Making under On-Ramp merge Scenarios by Distributional Soft Actor-Critic Algorithm
- Weather Analogs with a Machine Learning Similarity Metric for Renewable Resource Forecasting
- Self-Supervised Online Reward Shaping in Sparse-Reward Environments
- One-Shot Medical Landmark Detection
- Incremental Learning for Multi-organ Segmentation with Partially Labeled Datasets
- FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation
- Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization
- "Sharks are not the threat humans are": Argument Component Segmentation in School Student Essays
- Loosely Synchronized Search for Multi-agent Path Finding with Asynchronous Actions
- Nondeterminism and Instability in Neural Network Optimization
- Improving Global Adversarial Robustness Generalization With Adversarially Trained GAN
- An Energy-Saving Snake Locomotion Gait Policy Obtained Using Deep Reinforcement Learning
- Predictive Visual Tracking: A New Benchmark and Baseline Approach
- OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection
- End-to-End Human Object Interaction Detection with HOI Transformer
- Let's be friends! A rapport-building 3D embodied conversational agent for the Human Support Robot
- Sparsification for Fast Optimal Multi-Robot Path Planning in Lazy Compilation Schemes
- Fully Convolutional Geometric Features for Category-level Object Alignment
- Localization and Mapping using Instance-specific Mesh Models