Papers
Fri 26 Mar 2021
167 papers
- Increasing the Efficiency of Policy Learning for Autonomous Vehicles by Multi-Task Representation LearningEnd-to-end autonomous driving → Reinforcement learning for driving
- Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
- Distilling Object Detectors via Decoupled FeaturesKnowledge distillation → Detection and dense prediction distillation
- Distilling a Powerful Student Model via Online Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Multimodal Knowledge ExpansionKnowledge distillation → Multimodal distillation
- Hands-on Guidance for Distilling Object DetectorsKnowledge distillation → Detection and dense prediction distillation
- Imitation Learning from MPC for Quadrupedal Multi-Gait ControlOffline RL and imitation learning from data → Imitation learning methods
- BART based semantic correction for Mandarin automatic speech recognition system
- Implementing an expert system to evaluate technical solutions innovativeness
- Dynamic Domain Adaptation for Efficient Inference
- Systematic Mapping Protocol: Reasoning Algorithms on Feature Model
- TOUR: Dynamic Topic and Sentiment Analysis of User Reviews for Assisting App Release
- Multi-source Transfer Learning with Ensemble for Financial Time Series Forecasting
- Current Trends and Applications of Dempster-Shafer Theory (Review)
- Explore the Knowledge contained in Network Weights to Obtain Sparse Neural Networks
- Backpropagation Through Time For Networks With Long-Term Dependencies
- Contrastive Domain Adaptation
- Categorical Representation Learning: Morphism is All You Need
- An Automated Multiple-Choice Question Generation Using Natural Language Processing Techniques
- Equivariant Imaging: Learning Beyond the Range Space
- Survival Regression with Proper Scoring Rules and Monotonic Neural Networks
- Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks
- Leaky Nets: Recovering Embedded Neural Network Models and Inputs through Simple Power and Timing Side-Channels -- Attacks and Defenses
- Construction of a Large-scale Japanese ASR Corpus on TV Recordings
- Fully Automated 2D and 3D Convolutional Neural Networks Pipeline for Video Segmentation and Myocardial Infarction Detection in Echocardiography
- Modeling the Nonsmoothness of Modern Neural Networks
- Risk-Averse Stochastic Shortest Path Planning
- When Few-Shot Learning Meets Video Object Detection
- Lower Bounds on the Generalization Error of Nonlinear Learning Models
- Almost Surely Stable Deep Dynamics
- Generating and Evaluating Explanations of Attended and Error-Inducing Input Regions for VQA Models
- Tuning IR-cut Filter for Illumination-aware Spectral Reconstruction from RGB
- Focused LRP: Explainable AI for Face Morphing Attack Detection
- Exploiting Adam-like Optimization Algorithms to Improve the Performance of Convolutional Neural Networks
- Generalization capabilities of translationally equivariant neural networks
- Synthesis of Compositional Animations from Textual Descriptions
- Multi-Modal RGB-D Scene Recognition Across Domains
- Autonomous Overtaking in Gran Turismo Sport Using Curriculum Reinforcement Learning
- Multi-Disease Detection in Retinal Imaging based on Ensembling Heterogeneous Deep Learning Models
- Alignment of Language Agents
- Quantum Self-Supervised Learning
- Baking Neural Radiance Fields for Real-Time View Synthesis
- Planar Surface Reconstruction from Sparse Views
- On Generating Transferable Targeted Perturbations
- A Practical Survey on Faster and Lighter Transformers
- PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
- Visionary: Vision architecture discovery for robot learning
- Hybrid analysis and modeling, eclecticism, and multifidelity computing toward digital twin revolution
- Dodrio: Exploring Transformer Models with Interactive Visualization
- Randomization-based Machine Learning in Renewable Energy Prediction Problems: Critical Literature Review, New Results and Perspectives
- LiGCN: Label-interpretable Graph Convolutional Networks for Multi-label Text Classification
- Training a Task-Specific Image Reconstruction Loss
- SKID RAW: Skill Discovery from Raw Trajectories
- On UMAP's true loss function
- Predicting Demand for Air Taxi Urban Aviation Services using Machine Learning Algorithms
- Data Quality as Predictor of Voice Anti-Spoofing Generalization
- Model-Free Learning of Safe yet Effective Controllers
- Understanding Robustness of Transformers for Image Classification
- Leveraging pre-trained representations to improve access to untranscribed speech from endangered languages
- Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation
- Correcting Automated and Manual Speech Transcription Errors using Warped Language Models
- GeoSP: A parallel method for a cortical surface parcellation based on geodesic distance
- Unsupervised Robust Domain Adaptation without Source Data
- Elvet -- a neural network-based differential equation and variational problem solver
- Sparse Object-level Supervision for Instance Segmentation with Pixel Embeddings
- Deep Unsupervised Learning for Generalized Assignment Problems: A Case-Study of User-Association in Wireless Networks
- DivAug: Plug-in Automated Data Augmentation with Explicit Diversity Maximization
- Unsupervised Document Embedding via Contrastive Augmentation
- NL-EDIT: Correcting semantic parse errors through natural language interaction
- FeatureEnVi: Visual Analytics for Feature Engineering Using Stepwise Selection and Semi-Automatic Extraction Approaches
- Detection, growth quantification and malignancy prediction of pulmonary nodules using deep convolutional networks in follow-up CT scans
- 3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning
- Model-based Reconstruction with Learning: From Unsupervised to Supervised and Beyond
- On the hidden treasure of dialog in video question answering
- Improved Initialization of State-Space Artificial Neural Networks
- Continual Speaker Adaptation for Text-to-Speech Synthesis
- Agent with Warm Start and Adaptive Dynamic Termination for Plane Localization in 3D Ultrasound
- RCT: Resource Constrained Training for Edge AI
- Probabilistic Planning with Preferences over Temporal Goals
- Composable Learning with Sparse Kernel Representations
- Multiple GAN Inversion for Exemplar-based Image-to-Image Translation
- Spatial Dual-Modality Graph Reasoning for Key Information Extraction
- Zero-shot Sequence Labeling for Transformer-based Sentence Classifiers
- Unsupervised Multi-Index Semantic Hashing
- Projected Hamming Dissimilarity for Bit-Level Importance Coding in Collaborative Filtering
- Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifiers
- Robot Program Parameter Inference via Differentiable Shadow Program Inversion
- Incorporating Connections Beyond Knowledge Embeddings: A Plug-and-Play Module to Enhance Commonsense Reasoning in Machine Reading Comprehension
- Visual Explanations from Spiking Neural Networks using Interspike Intervals
- Gated Transformer Networks for Multivariate Time Series Classification
- Generalized Planning as Heuristic Search
- Combining distribution-based neural networks to predict weather forecast probabilities
- Node metadata can produce predictability transitions in network inference problems
- On the Theory of Stochastic Automata
- SegVisRL: Visuomotor Development for a Lunar Rover for Hazard Avoidance using Camera Images
- Leveraging Historical Data for High-Dimensional Regression Adjustment, a Composite Covariate Approach
- YOLinO: Generic Single Shot Polyline Detection in Real Time
- Self-Supervised Learning in Multi-Task Graphs through Iterative Consensus Shift
- Functorial Language Models
- An Embedding-based Joint Sentiment-Topic Model for Short Texts
All 167
- LS-CAT: A Large-Scale CUDA AutoTuning Dataset
- Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow
- Online learning with exponential weights in metric spaces
- Geometric Affinity Propagation for Clustering with Network Knowledge
- Prior-Independent Auctions for the Demand Side of Federated Learning
- D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution
- A PSO Strategy of Finding Relevant Web Documents using a New Similarity Measure
- VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptation
- The convergence of the Stochastic Gradient Descent (SGD) : a self-contained proof
- DAGN: Discourse-Aware Graph Network for Logical Reasoning
- Combating Adversaries with Anti-Adversaries
- MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learning
- MedSelect: Selective Labeling for Medical Image Classification Combining Meta-Learning with Deep Reinforcement Learning
- Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling
- Geometry-Aware Unsupervised Domain Adaptation for Stereo Matching
- Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation
- Guided Training: A Simple Method for Single-channel Speaker Separation
- Online structural health monitoring by model order reduction and deep learning algorithms
- Bidirectional Projection Network for Cross Dimension Scene Understanding
- City-scale Scene Change Detection using Point Clouds
- Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation
- Mutually-Constrained Monotonic Multihead Attention for Online ASR
- Evaluation of Preprocessing Techniques for U-Net Based Automated Liver Segmentation
- Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots
- Vulnerability Due to Training Order in Split Learning
- IMU Data Processing For Inertial Aided Navigation: A Recurrent Neural Network Based Approach
- OmniHang: Learning to Hang Arbitrary Objects using Contact Point Correspondences and Neural Collision Estimation
- Rethinking Graph Neural Architecture Search from Message-passing
- DDR-Net: Learning Multi-Stage Multi-View Stereo With Dynamic Depth Range
- Character Controllers Using Motion VAEs
- LightSAL: Lightweight Sign Agnostic Learning for Implicit Surface Representation
- Hierarchical Federated Learning with Quantization: Convergence Analysis and System Design
- Input-Output Balanced Framework for Long-tailed LiDAR Semantic Segmentation
- Confluent Vessel Trees with Accurate Bifurcations
- Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
- Provably Correct Controller Synthesis of Switched Stochastic Systems with Metric Temporal Logic Specifications: A Case Study on Power Systems
- Robust Pandemic Control Synthesis with Formal Specifications: A Case Study on COVID-19 Pandemic
- OTA: Optimal Transport Assignment for Object Detection
- Learning to Track with Object Permanence
- Learning Reactive and Predictive Differentiable Controllers for Switching Linear Dynamical Models
- Mixing-AdaSIN: Constructing a De-biased Dataset using Adaptive Structural Instance Normalization and Texture Mixing
- Supervised Chorus Detection for Popular Music Using Convolutional Neural Network and Multi-task Learning
- Embedding Power Flow into Machine Learning for Parameter and State Estimation
- Evaluation of deep learning models for multi-step ahead time series prediction
- Marine Snow Removal Benchmarking Dataset
- Super-Resolving Compressed Video in Coding Chain
- Improve GAN-based Neural Vocoder using Pointwise Relativistic LeastSquare GAN
- Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation
- FRITL: A Hybrid Method for Causal Discovery in the Presence of Latent Confounders
- ACRE: Abstract Causal REasoning Beyond Covariation
- Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance
- Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution
- Active multi-fidelity Bayesian online changepoint detection
- Adversarial Attacks are Reversible with Natural Supervision
- Which Parts Determine the Impression of the Font?
- Synthesize-It-Classifier: Learning a Generative Classifier through RecurrentSelf-analysis
- MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakes
- Leaning Compact and Representative Features for Cross-Modality Person Re-Identification
- Modeling the Compatibility of Stem Tracks to Generate Music Mashups
- Towards a Unified Approach to Single Image Deraining and Dehazing
- Deep Two-Way Matrix Reordering for Relational Data Analysis
- Image2Reverb: Cross-Modal Reverb Impulse Response Synthesis
- Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection
- DBATES: DataBase of Audio features, Text, and visual Expressions in competitive debate Speeches
- Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs
- Deformable Linear Object Prediction Using Locally Linear Latent Dynamics
- Self-Attentive 3D Human Pose and Shape Estimation from Videos