Papers
Mon 12 Jul 2021
149 papers
- LANA: Latency Aware Network AccelerationKnowledge distillation → General knowledge distillation methods
- Conservative Offline Distributional Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Altruistic Maneuver Planning for Cooperative Autonomous Vehicles Using Multi-agent Advantage Actor-CriticEnd-to-end autonomous driving → Cooperative and V2X driving
- Behavior Constraining in Weight Space for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Technical Report of Team GraphMIRAcles in the WikiKG90M-LSC Track of OGB-LSC @ KDD Cup 2021Knowledge distillation → Graph neural network distillation
- Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoningLLM safety and security → Backdoor and data poisoning attacks
- Improvement of image classification by multiple optical scattering
- Project Achoo: A Practical Model and Application for COVID-19 Detection from Recordings of Breath, Voice, and Cough
- Lumen: A Machine Learning Framework to Expose Influence Cues in Text
- A Systematic Literature Review of Automated ICD Coding and Classification Systems using Discharge Summaries
- Regularized Classification-Aware Quantization
- Explore and Control with Adversarial Surprise
- Explainable AI: current status and future directions
- Tortured phrases: A dubious writing style emerging in science. Evidence of critical issues affecting established journals
- An Efficient Deep Distribution Network for Bid Shading in First-Price Auctions
- Trustworthy AI: A Computational Perspective
- Ontology-Based Process Modelling -- Will we live to see it?
- Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task
- Detect and Defense Against Adversarial Examples in Deep Learning using Natural Scene Statistics and Adaptive Denoising
- An active dendritic tree can mitigate fan-in limitations in superconducting neurons
- Fast and Explicit Neural View Synthesis
- Combiner: Full Attention Transformer with Sparse Computation Cost
- Effects of personality traits in predicting grade retention of Brazilian students
- Likelihood estimation of sparse topic distributions in topic models and its applications to Wasserstein document distance calculations
- Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses
- Kernel Continual Learning
- Reinforcement Learning based Proactive Control for Transmission Grid Resilience to Wildfire
- EvoBA: An Evolution Strategy as a Strong Baseline forBlack-Box Adversarial Attacks
- SoftHebb: Bayesian Inference in Unsupervised Hebbian Soft Winner-Take-All Networks
- Adapting to Misspecification in Contextual Bandits
- Detecting Ideal Instagram Influencer Using Social Network Analysis
- Generalization of graph network inferences in higher-order graphical models
- Toward Efficient Transfer Learning in 6G
- Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration
- A Closer Look at the Adversarial Robustness of Information Bottleneck Models
- Optimal input representation in neural systems at the edge of chaos
- Computational modelling and data-driven homogenisation of knitted membranes
- Bayesian Atlas Building with Hierarchical Priors for Subject-specific Regularization
- Few-shot Language Coordination by Modeling Theory of Mind
- Quantifying Explainability in NLP and Analyzing Algorithms for Performance-Explainability Tradeoff
- Revisiting Uncertainty-based Query Strategies for Active Learning with Transformers
- The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents
- Accenture at CheckThat! 2021: Interesting claim identification and ranking with contextually sensitive lexical training data augmentation
- Least-Squares Linear Dilation-Erosion Regressor Trained using a Convex-Concave Procedure
- Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions
- Codified audio language modeling learns useful representations for music information retrieval
- Quality of Service Guarantees for Physical Unclonable Functions
- Stress Classification and Personalization: Getting the most out of the least
- Locally Enhanced Self-Attention: Combining Self-Attention and Convolution as Local and Context Terms
- DDCNet-Multires: Effective Receptive Field Guided Multiresolution CNN for Dense Prediction
- Hierarchical Neural Dynamic Policies
- End-to-end Multi-modal Video Temporal Grounding
- Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains
- Let's Play for Action: Recognizing Activities of Daily Living by Learning from Life Simulation Video Games
- A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution
- Interpretable Mammographic Image Classification using Case-Based Reasoning and Deep Learning
- Direct speech-to-speech translation with discrete units
- Active Divergence with Generative Deep Learning -- A Survey and Taxonomy
- Nonlinear Least Squares for Large-Scale Machine Learning using Stochastic Jacobian Estimates
- Differentially Private Stochastic Optimization: New Results in Convex and Non-Convex Settings
- Few-shot Learning with Global Relatedness Decoupled-Distillation
- Forster Decomposition and Learning Halfspaces with Noise
- ProGS: Property Graph Shapes Language (Extended Version)
- LATTE: LSTM Self-Attention based Anomaly Detection in Embedded Automotive Platforms
- Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing
- Meta-learning PINN loss functions
- End-to-End Natural Language Understanding Pipeline for Bangla Conversational Agents
- 1st Place Solution for ICDAR 2021 Competition on Mathematical Formula Detection
- Deformation-Compensated Learning for Image Reconstruction without Ground Truth
- Context-aware virtual adversarial training for anatomically-plausible segmentation
- ROBIN: A Robust Optical Binary Neural Network Accelerator
- Multi-view Image-based Hand Geometry Refinement using Differentiable Monte Carlo Ray Tracing
- Recent advances in Bayesian optimization with applications to parameter reconstruction in optical nano-metrology
- Synthesizing Multi-Tracer PET Images for Alzheimer's Disease Patients using a 3D Unified Anatomy-aware Cyclic Adversarial Network
- Anatomy-Constrained Contrastive Learning for Synthetic Segmentation without Ground-truth
- GiT: Graph Interactive Transformer for Vehicle Re-identification
- Denoising User-aware Memory Network for Recommendation
- The Power of Proxy Data and Proxy Networks for Hyper-Parameter Optimization in Medical Image Segmentation
- Visual-Tactile Cross-Modal Data Generation using Residue-Fusion GAN with Feature-Matching and Perceptual Losses
- Automated Label Generation for Time Series Classification with Representation Learning: Reduction of Label Cost for Training
- Improving the Algorithm of Deep Learning with Differential Privacy
- AxonEM Dataset: 3D Axon Instance Segmentation of Brain Cortical Regions
- Scenes and Surroundings: Scene Graph Generation using Relation Transformer
- Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration
- Bayesian brains and the R'enyi divergence
- CoBERL: Contrastive BERT for Reinforcement Learning
- MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition
- PonderNet: Learning to Ponder
- Learning Expected Emphatic Traces for Deep RL
- Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation
- Fine-Grained AutoAugmentation for Multi-Label Classification
- A Flexible Multi-Task Model for BERT Serving
- On the Evaluation of Commit Message Generation Models: An Experimental Study
- How to Approximate Ontology-Mediated Queries
- Hate versus Politics: Detection of Hate against Policy makers in Italian tweets
- Zero-shot Visual Question Answering using Knowledge Graph
- SimDem A Multi-agent Simulation Environment to Model Persons with Dementia and their Assistance
- Post Triangular Rewiring Method for Shorter RRT Robot Path Planning
- EndoUDA: A modality independent segmentation approach for endoscopy imaging
- Nonparametric Regression with Shallow Overparameterized Neural Networks Trained by GD with Early Stopping
All 149
- Visual Transformer with Statistical Test for COVID-19 Classification
- Sparse Personalized Federated Learning
- Structured Directional Pruning via Perturbation Orthogonal Projection
- Learning interaction rules from multi-animal trajectories via augmented behavioral models
- Metalearning Linear Bandits by Prior Update
- Human-like Relational Models for Activity Recognition in Video
- R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery
- Real-Time Super-Resolution System of 4K-Video Based on Deep Learning
- HEMP: High-order Entropy Minimization for neural network comPression
- DaCy: A Unified Framework for Danish NLP
- Continuous Time Bandits With Sampling Costs
- End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB
- ICDAR 2021 Competition on Integrated Circuit Text Spotting and Aesthetic Assessment
- Constrained Sampling from a Kernel Density Estimator to Generate Scenarios for the Assessment of Automated Vehicles
- Geographical Knowledge-driven Representation Learning for Remote Sensing Images
- TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation
- Learned super resolution ultrasound for improved breast lesion characterization
- The Brownian motion in the transformer model
- AutoFB: Automating Fetal Biometry Estimation from Standard Ultrasound Planes
- OmniLytics: A Blockchain-based Secure Data Market for Decentralized Machine Learning
- Modeling Explicit Concerning States for Reinforcement Learning in Visual Dialogue
- Impact of Energy Efficiency on the Morphology and Behaviour of Evolved Robots
- Prb-GAN: A Probabilistic Framework for GAN Modelling
- Training of deep cross-modality conversion models with a small dataset, and their application in megavoltage CT to kilovoltage CT conversion
- Position-enhanced and Time-aware Graph Convolutional Network for Sequential Recommendations
- Predicting sepsis in multi-site, multi-national intensive care cohorts using deep learning
- Fock State-enhanced Expressivity of Quantum Machine Learning Models
- BERT-like Pre-training for Symbolic Piano Music Classification Tasks
- Perceptual-based deep-learning denoiser as a defense against adversarial attacks on ASR systems
- CatVRNN: Generating Category Texts via Multi-task Learning
- Cautious Actor-Critic
- A Simple Reward-free Approach to Constrained Reinforcement Learning
- Split, embed and merge: An accurate table structure recognizer
- Sliding Spectrum Decomposition for Diversified Recommendation
- Delta Sampling R-BERT for limited data and low-light action recognition
- Deep Risk Model: A Deep Learning Solution for Mining Latent Risk Factors to Improve Covariance Matrix Estimation
- Legal Judgment Prediction with Multi-Stage CaseRepresentation Learning in the Real Court Setting
- Deep-learning-based Hyperspectral imaging through a RGB camera
- TransClaw U-Net: Claw U-Net with Transformers for Medical Image Segmentation
- Polynomial Time Reinforcement Learning in Factored State MDPs with Linear Value Functions
- Early warning of pedestrians and cyclists
- AoI-minimizing Scheduling in UAV-relayed IoT Networks
- MugRep: A Multi-Task Hierarchical Graph Representation Learning Framework for Real Estate Appraisal
- Zero-Shot Compositional Concept Learning
- Deep Transfer Learning Based Intrusion Detection System for Electric Vehicular Networks
- Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations
- Stateful Detection of Model Extraction Attacks
- Spatial and Temporal Networks for Facial Expression Recognition in the Wild Videos
- MOOCRep: A Unified Pre-trained Embedding of MOOC Entities