Papers
Thu 21 Oct 2021
185 papers
- Off-Dynamics Inverse Reinforcement Learning from Hetero-DomainOffline RL and imitation learning from data → Inverse reinforcement learning
- Efficient Robotic Manipulation Through Offline-to-Online Reinforcement Learning and Goal-Aware State InformationOffline RL and imitation learning from data → Real-world robot offline RL
- Fourier Neural Networks for Function Approximation
- Degree-Based Random Walk Approach for Graph Embedding
- Technology Fitness Landscape for Design Innovation: A Deep Neural Embedding Approach Based on Patent Data
- Model-based Reinforcement Learning for Service Mesh Fault Resiliency in a Web Application-level
- Learning to run a power network with trust
- Hamiltonian Monte Carlo with Asymmetrical Momentum Distributions
- A First Polynomial Non-Clausal Class in Many-Valued Logic
- Automated Scoring System of HER2 in Pathological Images under the Microscope
- Wide Neural Networks Forget Less Catastrophically
- Digital and Physical-World Attacks on Remote Pulse Detection
- Sequential Voting with Relational Box Fields for Active Object Detection
- SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching
- Cortico-cerebellar networks as decoupling neural interfaces
- Wav2CLIP: Learning Robust Audio Representations From CLIP
- SymbioLCD: Ensemble-Based Loop Closure Detection using CNN-Extracted Objects and Visual Bag-of-Words
- Supporting Massive DLRM Inference Through Software Defined Memory
- Boosting Resource-Constrained Federated Learning Systems with Guessed Updates
- Representations of epistemic uncertainty and awareness in data-driven strategies
- Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition
- MixNorm: Test-Time Adaptation Through Online Normalization Estimation
- Conditioning of Random Feature Matrices: Double Descent and Generalization Error
- AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation
- Power Transformer Fault Diagnosis with Intrinsic Time-scale Decomposition and XGBoost Classifier
- MLPerf HPC: A Holistic Benchmark Suite for Scientific Machine Learning on HPC Systems
- FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping
- MUGL: Large Scale Multi Person Conditional Action Generation with Locomotion
- An EMD-based Method for the Detection of Power Transformer Faults with a Hierarchical Ensemble Classifier
- ML with HE: Privacy Preserving Machine Learning Inferences for Genome Studies
- Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent
- (Optimal) Online Bipartite Matching with Degree Information
- Generating Multivariate Load States Using a Conditional Variational Autoencoder
- Categorizing Items with Short and Noisy Descriptions using Ensembled Transferred Embeddings
- How can classical multidimensional scaling go wrong?
- A Machine Learning Framework Towards Transparency in Experts' Decision Quality
- Analysis of memory consumption by neural networks based on hyperparameters
- Fast Graph Sampling for Short Video Summarization using Gershgorin Disc Alignment
- PROVES: Establishing Image Provenance using Semantic Signatures
- Statistical discrimination in learning agents
- On the Regularization of Autoencoders
- DEX: Domain Embedding Expansion for Generalized Person Re-identification
- An Adaptive Digital Autopilot for Fixed-Wing Aircraft with Actuator Faults
- Self-Initiated Open World Learning for Autonomous AI Agents
- Decentralised Person Re-Identification with Selective Knowledge Aggregation
- Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes
- Efficient and Robust Mixed-Integer Optimization Methods for Training Binarized Deep Neural Networks
- CaloFlow II: Even Faster and Still Accurate Generation of Calorimeter Showers with Normalizing Flows
- Convex Joint Graph Matching and Clustering via Semidefinite Relaxations
- Generalized Out-of-Distribution Detection: A Survey
- Detecting Anti-Vaccine Users on Twitter
- QuantumNAT: Quantum Noise-Aware Training with Noise Injection, Quantization and Normalization
- A Fine-Grained Analysis on Distribution Shift
- Learning 3D Semantic Segmentation with only 2D Image Supervision
- StyleAlign: Analysis and Applications of Aligned StyleGAN Models
- Deep Curriculum Learning in Task Space for Multi-Class Based Mammography Diagnosis
- CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP
- Center Loss Regularization for Continual Learning
- Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation
- Fast Model Editing at Scale
- On games and simulators as a platform for development of artificial intelligence for command and control
- Survival-oriented embeddings for improving accessibility to complex data structures
- Transformer Acceleration with Dynamic Sparse Attention
- Video and Text Matching with Conditioned Embeddings
- An Empirical Study on GANs with Margin Cosine Loss and Relativistic Discriminator
- OpenABC-D: A Large-Scale Dataset For Machine Learning Guided Integrated Circuit Synthesis
- Likelihood Training of Schr"odinger Bridge using Forward-Backward SDEs Theory
- Physical Side-Channel Attacks on Embedded Neural Networks: A Survey
- One-Shot Transfer Learning of Physics-Informed Neural Networks
- Multi-Object Tracking and Segmentation with a Space-Time Memory Network
- The Effect of Wearing a Face Mask on Face Image Quality
- Fusion of complementary 2D and 3D mesostructural datasets using generative adversarial networks
- Actor-critic is implicitly biased towards high entropy optimal policies
- Self-Supervised Monocular Scene Decomposition and Depth Estimation
- Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimation
- Modeling the AC Power Flow Equations with Optimally Compact Neural Networks: Application to Unit Commitment
- Deep Reinforcement Learning for Online Control of Stochastic Partial Differential Equations
- MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification
- Detecting Important Patterns Using Conceptual Relevance Interestingness Measure
- Principal Component Analysis versus Factor Analysis
- On Optimal Interpolation In Linear Regression
- Multi-Category Mesh Reconstruction From Image Collections
- On the properties of some low-parameter models for color reproduction in terms of spectrum transformations and coverage of a color triangle
- Learning to Recommend Using Non-Uniform Data
- Variational Predictive Routing with Nested Subjective Timescales
- Detection of Driver Drowsiness by Calculating the Speed of Eye Blinking
- Is High Variance Unavoidable in RL? A Case Study in Continuous Control
- PlaneRecNet: Multi-Task Learning with Cross-Task Consistency for Piece-Wise Plane Detection and Reconstruction from a Single RGB Image
- User-friendly introduction to PAC-Bayes bounds
- User-Level Private Learning via Correlated Sampling
- Topic-Guided Abstractive Multi-Document Summarization
- Robustness through Data Augmentation Loss Consistency
- Anti-Concentrated Confidence Bonuses for Scalable Exploration
- Asynchronous Decentralized Distributed Training of Acoustic Models
- Generative Adversarial Graph Convolutional Networks for Human Action Synthesis
- On Hard Episodes in Meta-Learning
- SLURP: Side Learning Uncertainty for Regression Problems
- Sensing Cox Processes via Posterior Sampling and Positive Bases
- A Survey on Methods and Metrics for the Assessment of Explainability under the Proposed AI Act
- Modeling Performance in Open-Domain Dialogue with PARADISE
All 185
- Self-Supervised Visual Representation Learning Using Lightweight Architectures
- Each Attribute Matters: Contrastive Attention for Sentence-based Image Editing
- DMS, AE, DAA: methods and applications of adaptive time series model selection, ensemble, and financial evaluation
- DeLag: Using Multi-Objective Optimization to Enhance the Detection of Latency Degradation Patterns in Service-based Systems
- Personalized Transfer of User Preferences for Cross-domain Recommendation
- Lottery Tickets with Nonzero Biases
- HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification
- RCT: Random Consistency Training for Semi-supervised Sound Event Detection
- Dual Encoding U-Net for Spatio-Temporal Domain Shift Frame Prediction
- Statistical Finite Elements via Langevin Dynamics
- Inverse Optimal Control Adapted to the Noise Characteristics of the Human Sensorimotor System
- A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning
- Improving Non-autoregressive Generation with Mixup Training
- A Deep Insight into Measuring Face Image Utility with General and Face-specific Image Quality Metrics
- Applying Second-Order Quantifier Elimination in Inspecting G"odel's Ontological Proof
- Extraction of Positional Player Data from Broadcast Soccer Videos
- Reinforcement Learning Based Optimal Camera Placement for Depth Observation of Indoor Scenes
- RoMA: a Method for Neural Network Robustness Measurement and Assessment
- Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image Classification
- Robust Edge-Direct Visual Odometry based on CNN edge detection and Shi-Tomasi corner optimization
- Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation
- K-Lane: Lidar Lane Dataset and Benchmark for Urban Roads and Highways
- Bayesian Meta-Learning Through Variational Gaussian Processes
- Improving the Deployment of Recycling Classification through Efficient Hyper-Parameter Analysis
- RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation
- FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusion
- Watermarking Graph Neural Networks based on Backdoor Attacks
- Augmenting Knowledge Distillation With Peer-To-Peer Mutual Learning For Model Compression
- Learning Time-Varying Graphs from Online Data
- A Utility Maximization Model of Pedestrian and Driver Interactions
- Spatial Location Constraint Prototype Loss for Open Set Recognition
- Towards Reducing Aleatoric Uncertainty for Medical Imaging Tasks
- Bristle: Decentralized Federated Learning in Byzantine, Non-i.i.d. Environments
- Pixel-Level Face Image Quality Assessment for Explainable Face Recognition
- Mean Nystr"om Embeddings for Adaptive Compressive Learning
- Interpretable Machine Learning for Resource Allocation with Application to Ventilator Triage
- Learning OFDM Waveforms with PAPR and ACLR Constraints
- Optimizing Multi-Taper Features for Deep Speaker Verification
- LOA: Logical Optimal Actions for Text-based Interaction Games
- Efficient Gradient Flows in Sliced-Wasserstein Space
- Memory Efficient Adaptive Attention For Multiple Domain Learning
- Weakly Supervised Training of Monocular 3D Object Detectors Using Wide Baseline Multi-view Traffic Camera Data
- 2020 CATARACTS Semantic Segmentation Challenge
- Neuro-Symbolic Reinforcement Learning with First-Order Logic
- Individualized Decision-Making Under Partial Identification: Three Perspectives, Two Optimality Results, and One Paradox
- Vis-TOP: Visual Transformer Overlay Processor
- Data splitting improves statistical performance in overparametrized regimes
- Multi-label Classification with Partial Annotations using Class-aware Selective Loss
- MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation
- Multimodal Learning using Optimal Transport for Sarcasm and Humor Detection
- Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness
- A channel attention based MLP-Mixer network for motor imagery decoding with EEG
- Autonomous Dimension Reduction by Flattening Deformation of Data Manifold under an Intrinsic Deforming Field
- Can Q-learning solve Multi Armed Bantids?
- Subspace Detours Meet Gromov-Wasserstein
- Quantum field theories, Markov random fields and machine learning
- SecureBoost+: Large Scale and High-Performance Vertical Federated Gradient Boosting Decision Tree
- PipAttack: Poisoning Federated Recommender Systems forManipulating Item Promotion
- CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization
- Exploiting Inter-pixel Correlations in Unsupervised Domain Adaptation for Semantic Segmentation
- On some theoretical limitations of Generative Adversarial Networks
- An Empirical Evaluation of Time-Series Feature Sets
- Single-Modal Entropy based Active Learning for Visual Question Answering
- A Fast Location Algorithm for Very Sparse Point Clouds Based on Object Detection
- LARNet: Latent Action Representation for Human Action Synthesis
- Deep Image Matting with Flexible Guidance Input
- Privacy-Aware Identity Cloning Detection based on Deep Forest
- Least-Squares Neural Network (LSNN) Method For Scalar Nonlinear Hyperbolic Conservation Laws: Discrete Divergence Operator
- Evaluation of Various Open-Set Medical Imaging Tasks with Deep Neural Networks
- A Real-Time Energy and Cost Efficient Vehicle Route Assignment Neural Recommender System
- Evolving Transferable Neural Pruning Functions
- CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Level
- Controllable and Compositional Generation with Latent-Space Energy-Based Models
- HENet: Forcing a Network to Think More for Font Recognition
- Principled Representation Learning for Entity Alignment
- LC3Net: Ladder context correlation complementary network for salient object detection
- Class-Discriminative CNN Compression
- Deep Generative Models in Engineering Design: A Review
- Utilizing Redundancy in Cost Functions for Resilience in Distributed Optimization and Learning
- Using NASA Satellite Data Sources and Geometric Deep Learning to Uncover Hidden Patterns in COVID-19 Clinical Severity
- SMOF: Squeezing More Out of Filters Yields Hardware-Friendly CNN Pruning
- A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translation
- Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization
- High-resolution rainfall-runoff modeling using graph neural network
- Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization