Papers
Tue 23 Feb 2021
136 papers
- Learning to Drop Points for LiDAR Scan SynthesisWorld models → World modeling from LiDAR generation
- Enhancing Data-Free Adversarial Distillation with Activation Regularization and Virtual InterpolationKnowledge distillation → General knowledge distillation methods
- DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
- Automatic Borescope Damage Assessments for Gas Turbine Blades via Deep Learning
- Learning Large-scale Location Embedding From Human Mobility Trajectories with Graphs
- The Power of D-hops in Matching Power-Law Graphs
- Learning High-Order Interactions via Targeted Pattern Search
- A microservice-based framework for exploring data selection in cross-building knowledge transfer
- Controlling nonlinear dynamical systems into arbitrary states using machine learning
- Bridging Breiman's Brook: From Algorithmic Modeling to Statistical Learning
- Learner-Private Convex Optimization
- Do Transformer Modifications Transfer Across Implementations and Applications?
- Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases
- The SpaceNet Multi-Temporal Urban Development Challenge
- Location Trace Privacy Under Conditional Priors
- Arguments for the Unsuitability of Convolutional Neural Networks for Non--Local Tasks
- State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards
- Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others
- Non-Singular Adversarial Robustness of Neural Networks
- Feature Importance Explanations for Temporal Black-Box Models
- On Meritocracy in Optimal Set Selection
- Estimating Average Treatment Effects with Support Vector Machines
- The Sensitivity of Word Embeddings-based Author Detection Models to Semantic-preserving Adversarial Perturbations
- Event Camera Based Real-Time Detection and Tracking of Indoor Ground Robots
- Instance Specific Approximations for Submodular Maximization
- Grounded Relational Inference: Domain Knowledge Driven Explainable Autonomous Driving
- A Review of Generalizability and Transportability
- Neural ranking models for document retrieval
- Honey, I Shrunk The Actor: A Case Study on Preserving Performance with Smaller Actors in Actor-Critic RL
- Quantum Cross Entropy and Maximum Likelihood Principle
- Clustering Aware Classification for Risk Prediction and Subtyping in Clinical Data
- UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering
- Machine Learning Regression for Operator Dynamics
- Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality
- Probabilistic Spatial Analysis in Quantitative Microscopy with Uncertainty-Aware Cell Detection using Deep Bayesian Regression of Density Maps
- Generative Modelling of BRDF Textures from Flash Images
- Automated Discovery of Adaptive Attacks on Adversarial Defenses
- STEP: Segmenting and Tracking Every Pixel
- Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning
- Deep Unitary Convolutional Neural Networks
- An Explainable Artificial Intelligence Approach for Unsupervised Fault Detection and Diagnosis in Rotating Machinery
- Learning with User-Level Privacy
- Convergence rates for gradient descent in the training of overparameterized artificial neural networks with piecewise affine activation
- Page Layout Analysis System for Unconstrained Historic Documents
- Solving high-dimensional parabolic PDEs using the tensor train format
- Online Stochastic Gradient Descent Learns Linear Dynamical Systems from A Single Trajectory
- Dynamic Neural Garments
- Data-driven analysis of central bank digital currency (CBDC) projects drivers
- Inferring Agents Preferences as Priors for Probabilistic Goal Recognition
- QuPeL: Quantized Personalization with Applications to Federated Learning
- Ray-based framework for state identification in quantum dot devices
- Parameterized Complexity of Logic-Based Argumentation in Schaefer's Framework
- Federated Learning for Physical Layer Design
- Improving Deep Learning Sound Events Classifiers using Gram Matrix Feature-wise Correlations
- School of hard knocks: Curriculum analysis for Pommerman with a fixed computational budget
- SBI: A Simulation-Based Test of Identifiability for Bayesian Causal Inference
- EBMs Trained with Maximum Likelihood are Generator Models Trained with a Self-adverserial Loss
- Deep Policy Dynamic Programming for Vehicle Routing Problems
- Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problems
- Paraphrases do not explain word analogies
- Uncertainty-aware Generalized Adaptive CycleGAN
- Weakly-supervised multi-class object localization using only object counts as labels
- Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed
- Recurrent Model Predictive Control
- Rethinking Natural Adversarial Examples for Classification Models
- RGB-D Railway Platform Monitoring and Scene Understanding for Enhanced Passenger Safety
- Deep Unrolled Network for Video Super-Resolution
- Greedy-Step Off-Policy Reinforcement Learning
- Multi-Space Evolutionary Search for Large-Scale Optimization
- A System for 3D Reconstruction Of Comminuted Tibial Plafond Bone Fractures
- Cell abundance aware deep learning for cell detection on highly imbalanced pathological data
- Measuring Data Leakage in Machine-Learning Models with Fisher Information
- A Goodness-of-fit Test on the Number of Biclusters in a Relational Data Matrix
- Learning to Fairly Classify the Quality of Wireless Links
- A Novel Deep Learning Method for Textual Sentiment Analysis
- Unsupervised Brain Anomaly Detection and Segmentation with Transformers
- HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search
- FINE Samples for Learning with Noisy Labels
- Models we Can Trust: Toward a Systematic Discipline of (Agent-Based) Model Interpretation and Validation
- Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptation
- SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition
- ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks
- Gradient-adjusted Incremental Target Propagation Provides Effective Credit Assignment in Deep Neural Networks
- Strategic Classification in the Dark
- Data Fusion for Audiovisual Speaker Localization: Extending Dynamic Stream Weights to the Spatial Domain
- Adversarial Examples Detection beyond Image Space
- ROAD: The ROad event Awareness Dataset for Autonomous Driving
- Enhancing Model Robustness By Incorporating Adversarial Knowledge Into Semantic Representation
- Deep Deterministic Uncertainty: A Simple Baseline
- Automated Quality Assessment of Cognitive Behavioral Therapy Sessions Through Highly Contextualized Language Representations
- Robust and Transferable Anomaly Detection in Log Data using Pre-Trained Language Models
- Artificial Intelligence as an Anti-Corruption Tool (AI-ACT) -- Potentials and Pitfalls for Top-down and Bottom-up Approaches
- Multi-Knowledge Fusion for New Feature Generation in Generalized Zero-Shot Learning
- SISE-PC: Semi-supervised Image Subsampling for Explainable Pathology
- EscapeWildFire: Assisting People to Escape Wildfires in Real-Time
- Accelerating Recursive Partition-Based Causal Structure Learning
- Identifying Physical Law of Hamiltonian Systems via Meta-Learning
- Deep Deformation Detail Synthesis for Thin Shell Models
- Decision Rule Elicitation for Domain Adaptation
- Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization
All 136
- Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
- Accurate Learning of Graph Representations with Graph Multiset Pooling
- Memory-efficient Speech Recognition on Smart Devices
- Domain-invariant NBV Planner for Active Cross-domain Self-localization
- Differentiable Logic Machines
- Enhanced Modality Transition for Image Captioning
- Automatic Ship Classification Utilizing Bag of Deep Features
- Classification of Breast Cancer Lesions in Ultrasound Images by using Attention Layer and loss Ensembles in Deep Convolutional Neural Networks
- SliceNStitch: Continuous CP Decomposition of Sparse Tensor Streams
- Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and model
- Comparative evaluation of CNN architectures for Image Caption Generation
- Equivariant neural networks for inverse problems
- Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution
- Oriole: Thwarting Privacy against Trustworthy Deep Learning Models
- Model-Attentive Ensemble Learning for Sequence Modeling
- V2W-BERT: A Framework for Effective Hierarchical Multiclass Classification of Software Vulnerabilities
- Controllable and Diverse Text Generation in E-commerce
- Anytime Sampling for Autoregressive Models via Ordered Autoencoding
- Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games
- Senone-aware Adversarial Multi-task Training for Unsupervised Child to Adult Speech Adaptation
- When is Early Classification of Time Series Meaningful?
- Generalized Equivariance and Preferential Labeling for GNN Node Classification
- Structural Similarity of Boundary Conditions and an Efficient Local Search Algorithm for Goal Conflict Identification
- Evolutionary optimization of contexts for phonetic correction in speech recognition systems
- Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks
- VisualCheXbert: Addressing the Discrepancy Between Radiology Report Labels and Image Labels
- FaceController: Controllable Attribute Editing for Face in the Wild
- Representation Disentanglement for Multi-modal brain MR Analysis
- Neuroscience-Inspired Algorithms for the Predictive Maintenance of Manufacturing Systems
- MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning
- Data Engineering for Everyone
- Assigning Confidence to Molecular Property Prediction
- Model-Based Domain Generalization
- Histo-fetch -- On-the-fly processing of gigapixel whole slide images simplifies and speeds neural network training
- Optimal Prediction Intervals for Macroeconomic Time Series Using Chaos and NSGA II
- Factorization of Fact-Checks for Low Resource Indian Languages