Papers
Fri 9 Jul 2021
159 papers
- Lifelong Mixture of Variational AutoencodersMixture-of-experts → Mixture of LoRA experts
- Lifelong Teacher-Student Network LearningKnowledge distillation → General knowledge distillation methods
- Offline reinforcement learning with uncertainty for treatment strategies in sepsisOffline RL and imitation learning from data → Safe offline RL
- ARC: Adversarially Robust Control Policies for Autonomous VehiclesEnd-to-end autonomous driving → Adversarial scenarios and safety testing
- Adversarial Mixture Density Networks: Learning to Drive Safely from Collision DataOffline RL and imitation learning from data → Imitation and offline RL for driving
- Continual Learning in the Teacher-Student Setup: Impact of Task SimilarityKnowledge distillation → Distillation for continual learning
- Segmentation of VHR EO Images using Unsupervised Learning
- ABD-Net: Attention Based Decomposition Network for 3D Point Cloud Decomposition
- Linear Prediction Residual for Efficient Diagnosis of Parkinson's Disease from Gait
- Federated Learning with Dynamic Transformer for Text to Speech
- FMNet: Latent Feature-wise Mapping Network for Cleaning up Noisy Micro-Doppler Spectrogram
- NVCell: Standard Cell Layout in Advanced Technology Nodes with Reinforcement Learning
- GGT: Graph-Guided Testing for Adversarial Sample Detection of Deep Neural Network
- Reinforced Hybrid Genetic Algorithm for the Traveling Salesman Problem
- Transformer-Based Behavioral Representation Learning Enables Transfer Learning for Mobile Sensing in Small Datasets
- Computer-Aided Diagnosis of Low Grade Endometrial Stromal Sarcoma (LGESS)
- U-Net with Hierarchical Bottleneck Attention for Landmark Detection in Fundus Images of the Degenerated Retina
- DDCNet: Deep Dilated Convolutional Neural Network for Dense Prediction
- A Topological-Framework to Improve Analysis of Machine Learning Model Performance
- Automated Graph Learning via Population Based Self-Tuning GCN
- Lifelong Twin Generative Adversarial Networks
- InfoVAEGAN : learning joint interpretable representations by information maximization and maximum likelihood
- L2M: Practical posterior Laplace approximation with optimization-driven second moment estimation
- An Initial Investigation of Non-Native Spoken Question-Answering
- Scaled-Time-Attention Robust Edge Network
- A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Data
- Noisy Training Improves E2E ASR for the Edge
- Gaussian Process Subspace Regression for Model Reduction
- H"older Bounds for Sensitivity Analysis in Causal Reasoning
- The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders
- Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
- Efficient Real-Time Image Recognition Using Collaborative Swarm of UAVs and Convolutional Networks
- Self-Supervised Generative Adversarial Network for Depth Estimation in Laparoscopic Images
- Escaping the Impossibility of Fairness: From Formal to Substantive Algorithmic Fairness
- Training Over-parameterized Models with Non-decomposable Objectives
- Playing Angry Birds with a Domain-Independent PDDL+ Planner
- Inferring Probabilistic Reward Machines from Non-Markovian Reward Processes for Reinforcement Learning
- Algorithmic Causal Effect Identification with causaleffect
- Ill-posed Surface Emissivity Retrieval from Multi-Geometry Hyperspectral Images using a Hybrid Deep Neural Network
- Cumulative Assessment for Urban 3D Modeling
- Diverse Video Generation using a Gaussian Process Trigger
- Optimal Triangulation Method is Not Really Optimal
- A deep convolutional neural network that is invariant to time rescaling
- ViTGAN: Training GANs with Vision Transformers
- ANCER: Anisotropic Certification via Sample-wise Volume Maximization
- Seven Basic Expression Recognition Using ResNet-18
- Deep Learning for Mean Field Games and Mean Field Control with Applications to Finance
- Multi-level Stress Assessment from ECG in a Virtual Reality Environment using Multimodal Fusion
- Universal Multilayer Network Exploration by Random Walk with Restart
- The Bayesian Learning Rule
- Deep Learning for Reduced Order Modelling and Efficient Temporal Evolution of Fluid Simulations
- Can Deep Neural Networks Predict Data Correlations from Column Names?
- White-Box Cartoonization Using An Extended GAN Framework
- Cross-modal Attention for MRI and Ultrasound Volume Registration
- Learning Interaction-aware Guidance Policies for Motion Planning in Dense Traffic Scenarios
- Modality specific U-Net variants for biomedical image segmentation: A survey
- Event-Based Feature Tracking in Continuous Time with Sliding Window Optimization
- Behavior Self-Organization Supports Task Inference for Continual Robot Learning
- Entropy, Information, and the Updating of Probabilities
- BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGym
- Learning Cascaded Detection Tasks with Weakly-Supervised Domain Adaptation
- Group-Node Attention for Community Evolution Prediction
- Online Adaptation to Label Distribution Shift
- Optimal Gradient-based Algorithms for Non-concave Bandit Optimization
- Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors
- Using Machine Translation to Localize Task Oriented NLG Output
- Hacking VMAF and VMAF NEG: vulnerability to different preprocessing methods
- Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression
- Semantic and Geometric Unfolding of StyleGAN Latent Space
- Bayesian Error-in-Variables Models for the Identification of Power Networks
- Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation
- MutualEyeContact: A conversation analysis tool with focus on eye contact
- Interpretable Compositional Convolutional Neural Networks
- ADAST: Attentive Cross-domain EEG-based Sleep Staging Framework with Iterative Self-Training
- A First Look at Class Incremental Learning in Deep Learning Mobile Traffic Classification
- Redescription Model Mining
- On the Challenges of Open World Recognitionunder Shifting Visual Domains
- Understanding the Distributions of Aggregation Layers in Deep Neural Networks
- Aligning an optical interferometer with beam divergence control and continuous action space
- Multimodal Icon Annotation For Mobile Applications
- A Deep Discontinuity-Preserving Image Registration Network
- A Comparison of Contextual and Non-Contextual Preference Ranking for Set Addition Problems
- Learning to Detect Adversarial Examples Based on Class Scores
- How to choose an Explainability Method? Towards a Methodical Implementation of XAI in Practice
- Multiaccurate Proxies for Downstream Fairness
- Policy Gradient Methods for Distortion Risk Measures
- Form2Seq : A Framework for Higher-Order Form Structure Extraction
- Multi-Modal Association based Grouping for Form Structure Extraction
- Block Alternating Bregman Majorization Minimization with Extrapolation
- Action Unit Detection with Joint Adaptive Attention and Graph Relation
- Hoechst Is All You Need: Lymphocyte Classification with Deep Learning
- Joint Matrix Decomposition for Deep Convolutional Neural Networks Compression
- Bib2Auth: Deep Learning Approach for Author Disambiguation using Bibliographic Data
- Specialists Outperform Generalists in Ensemble Classification
- Model compression as constrained optimization, with application to neural nets. Part V: combining compressions
- Rail Topology Ontology: A Rail Infrastructure Base Ontology
- Benchmarking for Biomedical Natural Language Processing Tasks with a Domain Specific ALBERT
- A Robust Deep Ensemble Classifier for Figurative Language Detection
- Multi-headed Neural Ensemble Search
- Lithography Hotspot Detection via Heterogeneous Federated Learning with Local Adaptation
All 159
- RGB Stream Is Enough for Temporal Action Detection
- Graph-based Deep Generative Modelling for Document Layout Generation
- An ontology for the formalization and visualization of scientific knowledge
- Generalization of the Change of Variables Formula with Applications to Residual Flows
- Attend2Pack: Bin Packing through Deep Reinforcement Learning with Attention
- StyleCariGAN: Caricature Generation via StyleGAN Feature Map Modulation
- Score refinement for confidence-based 3D multi-object tracking
- Semantic Segmentation on Multiple Visual Domains
- Mutually-aware Sub-Graphs Differentiable Architecture Search
- IDRLnet: A Physics-Informed Neural Network Library
- Prediction of butt rot volume in Norway spruce forest stands using harvester, remotely sensed and environmental data
- Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Dataset
- Autoencoder-driven Spiral Representation Learning for Gravitational Wave Surrogate Modelling
- Understanding surrogate explanations: the interplay between complexity, fidelity and coverage
- Hepatocellular Carcinoma Segmentation from Digital Subtraction Angiography Videos using Learnable Temporal Difference
- Integrating Planning, Execution and Monitoring in the presence of Open World Novelties: Case Study of an Open World Monopoly Solver
- Differentially private training of neural networks with Langevin dynamics for calibrated predictive uncertainty
- UniRE: A Unified Label Space for Entity Relation Extraction
- Task-Aware Sampling Layer for Point-Wise Analysis
- Retinal OCT Denoising with Pseudo-Multimodal Fusion Network
- Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset
- LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation
- JPGNet: Joint Predictive Filtering and Generative Network for Image Inpainting
- Fast Pixel-Matching for Video Object Segmentation
- Prior-Guided Multi-View 3D Head Reconstruction
- FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning
- Learning Syntactic Dense Embedding with Correlation Graph for Automatic Readability Assessment
- Sensitivity analysis in differentially private machine learning using hybrid automatic differentiation
- Towards Robust General Medical Image Segmentation
- Wavelet Transform-assisted Adaptive Generative Modeling for Colorization
- Unity Perception: Generate Synthetic Data for Computer Vision
- Structured Hammerstein-Wiener Model Learning for Model Predictive Control
- WinoCNN: Kernel Sharing Winograd Systolic Array for Efficient Convolutional Neural Network Acceleration on FPGAs
- Deep Image Synthesis from Intuitive User Input: A Review and Perspectives
- A Survey on Low-Resource Neural Machine Translation
- Blind Source Separation in Polyphonic Music Recordings Using Deep Neural Networks Trained via Policy Gradients
- Exploring Dropout Discriminator for Domain Adaptation
- A Dual-Purpose Deep Learning Model for Auscultated Lung and Tracheal Sound Analysis Based on Mixed Set Training
- Activated Gradients for Deep Neural Networks
- Multi-path Convolutional Neural Networks Efficiently Improve Feature Extraction in Continuous Adventitious Lung Sound Detection
- A Multi-task Mean Teacher for Semi-supervised Facial Affective Behavior Analysis
- Deep Learning models for benign and malign Ocular Tumor Growth Estimation
- Joint Models for Answer Verification in Question Answering Systems
- Measuring and Improving Model-Moderator Collaboration using Uncertainty Estimation
- On the Variance of the Fisher Information for Deep Learning
- Safe Exploration by Solving Early Terminated MDP
- REX: Revisiting Budgeted Training with an Improved Schedule
- Probabilistic Trajectory Prediction with Structural Constraints
- Emotion Recognition with Incomplete Labels Using Modified Multi-task Learning Technique
- Structured Model Pruning of Convolutional Networks on Tensor Processing Units
- Personalized Federated Learning over non-IID Data for Indoor Localization
- A Multi-modal and Multi-task Learning Method for Action Unit and Expression Recognition
- Greedy structure learning from data that contain systematic missing values
- EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments
- Safe Learning of Lifted Action Models
- Parallel and Multi-Objective Falsification with Scenic and VerifAI
- Towards Robust Active Feature Acquisition
- On lattice-free boosted MMI training of HMM and CTC-based full-context ASR models
- Levi Graph AMR Parser using Heterogeneous Attention