Papers
Wed 1 Sep 2021
149 papers
- Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge DistillationKnowledge distillation → On-policy and self-distillation for LLMs
- Implicit Behavioral CloningOffline RL and imitation learning from data → Imitation learning methods
- Optimization Networks for Integrated Machine Learning
- Stochastic Transformer Networks with Linear Competing Units: Application to end-to-end SL Translation
- Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions
- Machine Learning for Naval Architecture, Ocean and Marine Engineering
- Measuring Uncertainty in Signal Fingerprinting with Gaussian Processes Going Deep
- An Efficient Deep Learning Approach Using Improved Generative Adversarial Networks for Incomplete Information Completion of Self-driving
- Developing and validating multi-modal models for mortality prediction in COVID-19 patients: a multi-center retrospective study
- Acceleration Method for Learning Fine-Layered Optical Neural Networks
- Nonasymptotic one-and two-sample tests in high dimension with unknown covariance structure
- Multi-model Machine Learning Inference Serving with GPU Spatial Partitioning
- Black-Box Attacks on Sequential Recommenders via Data-Free Model Extraction
- Scalable Data Annotation Pipeline for High-Quality Large Speech Datasets Development
- Bilinear Input Normalization for Neural Networks in Financial Forecasting
- Domain Adaptive Cascade R-CNN for MItosis DOmain Generalization (MIDOG) Challenge
- You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection
- Sk-Unet Model with Fourier Domain for Mitosis Detection
- An Automated Approach for the Recognition of Bengali License Plates
- Assessing domain adaptation techniques for mitosis detection in multi-scanner breast cancer histopathology images
- Dash: Semi-Supervised Learning with Dynamic Thresholding
- The VoicePrivacy 2020 Challenge: Results and findings
- RIFLE: Imputation and Robust Inference from Low Order Marginals
- Searching for Efficient Multi-Stage Vision Transformers
- Properly learning decision trees in almost polynomial time
- Selecting Optimal Trace Clustering Pipelines with AutoML
- Field-Based Plot Extraction Using UAV RGB Images
- A Novel Multi-Centroid Template Matching Algorithm and Its Application to Cough Detection
- An Ensemble Approach for Annotating Source Code Identifiers with Part-of-speech Tags
- Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition
- Algorithme de recherche approximative dans un dictionnaire fond'e sur une distance d''edition d'efinie par blocs
- An End-to-End learnable Flow Regularized Model for Brain Tumor Segmentation
- Learning compositional programs with arguments and sampling
- LinEasyBO: Scalable Bayesian Optimization Approach for Analog Circuit Synthesis via One-Dimensional Subspaces
- An unsupervised framework for tracing textual sources of moral change
- Point-of-Interest Type Prediction using Text and Images
- Latin writing styles analysis with Machine Learning: New approach to old questions
- Streaming data preprocessing via online tensor recovery for large environmental sensor networks
- Wearable-based Classification of Running Styles with Deep Learning
- Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate Speech
- WebQA: Multihop and Multimodal QA
- Information-theoretic Classification Accuracy: A Criterion that Guides Data-driven Combination of Ambiguous Outcome Labels in Multi-class Classification
- FaVoA: Face-Voice Association Favours Ambiguous Speaker Detection
- Active label cleaning for improved dataset quality under resource constraints
- Pulmonary Disease Classification Using Globally Correlated Maximum Likelihood: an Auxiliary Attention mechanism for Convolutional Neural Networks
- DILBERT: Customized Pre-Training for Domain Adaptation withCategory Shift, with an Application to Aspect Extraction
- Does Knowledge Help General NLU? An Empirical Study
- Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Tasks
- Towards Improving Adversarial Training of NLP Models
- Shared Certificates for Neural Network Verification
- Active Inference and Epistemic Value in Graphical Models
- Variational Quantum Reinforcement Learning via Evolutionary Optimization
- Spatially and Robustly Hybrid Mixture Regression Model for Inference of Spatial Dependence
- Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems
- ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection
- ASVspoof 2021: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan
- The Minimax Complexity of Distributed Optimization
- R-SNN: An Analysis and Design Methodology for Robustifying Spiking Neural Networks against Adversarial Attacks through Noise Filters for Dynamic Vision Sensors
- TransforMesh: A Transformer Network for Longitudinal modeling of Anatomical Meshes
- Under-bagging Nearest Neighbors for Imbalanced Classification
- A Gradient Sampling Algorithm for Stratified Maps with Applications to Topological Data Analysis
- Wasserstein GANs with Gradient Penalty Compute Congested Transport
- Boosting Search Engines with Interactive Agents
- Physics-informed Neural Network for Nonlinear Dynamics in Fiber Optics
- On the Limits of Pseudo Ground Truth in Visual Camera Re-localisation
- Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification
- Conditional Extreme Value Theory for Open Set Video Domain Adaptation
- Don't Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques
- The Role of Explainability in Assuring Safety of Machine Learning in Healthcare
- Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction
- Survey of Low-Resource Machine Translation
- Impossibility Results in AI: A Survey
- Looking at the whole picture: constrained unsupervised anomaly segmentation
- Towards Learning a Vocabulary of Visual Concepts and Operators using Deep Neural Networks
- Capturing Stance Dynamics in Social Media: Open Challenges and Research Directions
- Sparse to Dense Motion Transfer for Face Image Animation
- Bayesian data combination model with Gaussian process latent variable model for mixed observed variables under NMAR missingness
- From Movement Kinematics to Object Properties: Online Recognition of Human Carefulness
- Weakly-Supervised Surface Crack Segmentation by Generating Pseudo-Labels using Localization with a Classifier and Thresholding
- The emergence of a concept in shallow neural networks
- Self-supervised Point Cloud Representation Learning via Separating Mixed Shapes
- Planning from video game descriptions
- Position Masking for Improved Layout-Aware Document Understanding
- Proceedings of KDD 2020 Workshop on Data-driven Humanitarian Mapping: Harnessing Human-Machine Intelligence for High-Stake Public Policy and Resilience Planning
- ReMeDi: Resources for Multi-domain, Multi-service, Medical Dialogues
- Masked Adversarial Generation for Neural Machine Translation
- Balancing Performance and Human Autonomy with Implicit Guidance Agent
- Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis
- EVReflex: Dense Time-to-Impact Prediction for Event-based Obstacle Avoidance
- Chronic Pain and Language: A Topic Modelling Approach to Personal Pain Descriptions
- An Integrated Framework for the Heterogeneous Spatio-Spectral-Temporal Fusion of Remote Sensing Images
- Boolean proportions
- Building a Legal Dialogue System: Development Process, Challenges and Opportunities
- ImageTBAD: A 3D Computed Tomography Angiography Image Dataset for Automatic Segmentation of Type-B Aortic Dissection
- Memory Based Video Scene Parsing
- ConRPG: Paraphrase Generation using Contexts as Regularizer
- Exploring deep learning methods for recognizing rare diseases and their clinical manifestations from texts
- Memory-Free Generative Replay For Class-Incremental Learning
- Category-Level Metric Scale Object Shape and Pose Estimation
- Intrinsic Argument Strength in Structured Argumentation: a Principled Approach
All 149
- BVMatch: Lidar-based Place Recognition Using Bird's-eye View Images
- ∞-former: Infinite Memory Transformer
- Discourse Analysis of Covid-19 in Persian Twitter Social Networks Using Graph Mining and Natural Language Processing
- Complex Event Forecasting with Prediction Suffix Trees: Extended Technical Report
- Discovering Representation Sprachbund For Multilingual Pre-Training
- Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs
- The Impact of Reinitialization on Generalization in Convolutional Neural Networks
- Extracting all Aspect-polarity Pairs Jointly in a Text with Relation Extraction Approach
- Aligning Cross-lingual Sentence Representations with Dual Momentum Contrast
- Seeing Implicit Neural Representations as Fourier Series
- Joint Graph Learning and Matching for Semantic Feature Correspondence
- OptAGAN: Entropy-based finetuning on text VAE-GAN
- Complexity Measures for Multi-objective Symbolic Regression
- Dataset for Identification of Homophobia and Transophobia in Multilingual YouTube Comments
- A Protection Method of Trained CNN Model Using Feature Maps Transformed With Secret Key From Unauthorized Access
- Spatio-Temporal Perturbations for Video Attribution
- Multi-Sample based Contrastive Loss for Top-k Recommendation
- Diverse Sample Generation: Pushing the Limit of Generative Data-free Quantization
- Efficient Person Search: An Anchor-Free Approach
- EventPoint: Self-Supervised Interest Point Detection and Description for Event-based Camera
- Fairness based Multi-Preference Resource Allocation in Decentralised Open Markets
- Federated Learning: Issues in Medical Application
- An Empirical Study on the Joint Impact of Feature Selection and Data Re-sampling on Imbalance Classification
- Pattern-based Acquisition of Scientific Entities from Scholarly Article Titles
- Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty Estimation
- Approximation Properties of Deep ReLU CNNs
- Evaluating Predictive Uncertainty under Distributional Shift on Dialogue Dataset
- Adapted End-to-End Coreference Resolution System for Anaphoric Identities in Dialogues
- Deep L1 Stochastic Optimal Control Policies for Planetary Soft-landing
- You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors
- CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations
- Perceptually Optimized Deep High-Dynamic-Range Image Tone Mapping
- Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds
- Problem Learning: Towards the Free Will of Machines
- What Have Been Learned & What Should Be Learned? An Empirical Study of How to Selectively Augment Text for Classification
- FADE: FAir Double Ensemble Learning for Observable and Counterfactual Outcomes
- Task-Oriented Communication for Multi-Device Cooperative Edge Inference
- Architecture Aware Latency Constrained Sparse Neural Networks
- An Unsupervised Method for Building Sentence Simplification Corpora in Multiple Languages
- Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces
- A Survey of Exploration Methods in Reinforcement Learning
- Asynchronous Federated Learning for Sensor Data with Concept Drift
- Federated Reconnaissance: Efficient, Distributed, Class-Incremental Learning
- Deep Dual Support Vector Data Description for Anomaly Detection on Attributed Networks
- Cognitive science as a source of forward and inverse models of human decisions for robotics and control
- Online Dynamic Window (ODW) Assisted Two-stage LSTM Frameworks for Indoor Localization
- A Weight Initialization Based on the Linear Product Structure for Neural Networks
- Learning Coated Adversarial Camouflages for Object Detectors
- FinQA: A Dataset of Numerical Reasoning over Financial Data