Papers
Fri 28 May 2021
181 papers
- Gotta Go Fast When Generating Data with Score-Based ModelsDiffusion models → Diffusion foundations and sampling
- Task-Guided Inverse Reinforcement Learning Under Partial InformationOffline RL and imitation learning from data → Inverse reinforcement learning
- Accelerating BERT Inference for Sequence Labeling via Early-ExitEfficient LLM inference and serving → Early exit and edge inference
- DiffSVC: A Diffusion Probabilistic Model for Singing Voice ConversionDiffusion models → Audio, speech and music
- AdvParams: An Active DNN Intellectual Property Protection Technique via Adversarial Perturbation Based Parameter EncryptionLLM safety and security → Watermarking generated content and models
- Transferable Deep Reinforcement Learning Framework for Autonomous Vehicles with Joint Radar-Data CommunicationsEnd-to-end autonomous driving → Cooperative and V2X driving
- FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation LearningKnowledge distillation → General knowledge distillation methods
- A BIC-based Mixture Model Defense against Data Poisoning Attacks on ClassifiersLLM safety and security → Backdoor and data poisoning attacks
- Predicting the Solar Potential of Rooftops using Image Segmentation and Structured Data
- Deep-learning based Tools for Automated Protocol Definition of Advanced Diagnostic Imaging Exams
- Using Machine Learning to Select High-Quality Measurements
- A Query-Driven Topic Model
- SciFive: a text-to-text transformer model for biomedical literature
- Short-term Maintenance Planning of Autonomous Trucks for Minimizing Economic Risk
- Deep Learning for EEG Seizure Detection in Preterm Infants
- Unsupervised detection of mouse behavioural anomalies using two-stream convolutional autoencoders
- KVT: k-NN Attention for Boosting Vision Transformers
- Highlight Timestamp Detection Model for Comedy Videos via Multimodal Sentiment Analysis
- Integer-Only Neural Network Quantization Scheme Based on Shift-Batch-Normalization
- Privately Learning Subspaces
- Comparing Two Different Approaches in Big Data and Business Analysis for Churn Prediction with the Focus on How Apache Spark Employed
- OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers
- Deep Fair Discriminative Clustering
- ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables
- On a class of data-driven mixed-integer programming problems under uncertainty: a distributionally robust approach
- Transformer-Based Source-Free Domain Adaptation
- 3D U-NetR: Low Dose Computed Tomography Reconstruction via Deep Learning and 3 Dimensional Convolutions
- Risk-Aware Transfer in Reinforcement Learning using Successor Features
- Joint Optimization of Multi-Objective Reinforcement Learning with Policy Gradient Based Algorithm
- Towards optimally abstaining from prediction with OOD test examples
- About Explicit Variance Minimization: Training Neural Networks for Medical Imaging With Limited Data Annotations
- Visualizing Representations of Adversarially Perturbed Inputs
- Towards More Equitable Question Answering Systems: How Much More Data Do You Need?
- Asymptotically Optimal Bandits under Weighted Information
- Goal Misgeneralization in Deep Reinforcement Learning
- MixerGAN: An MLP-Based Architecture for Unpaired Image-to-Image Translation
- Efficient and robust multi-task learning in the brain with modular latent primitives
- Smaller Is Better: An Analysis of Instance Quantity/Quality Trade-off in Rehearsal-based Continual Learning
- Reinforcement Learning reveals fundamental limits on the mixing of active particles
- An Attention Free Transformer
- Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learning
- Reinforcement Learning for on-line Sequence Transformation
- Weighted Training for Cross-Task Learning
- Galerkin Neural Networks: A Framework for Approximating Variational Equations with Error Control
- Cloud Collectives: Towards Cloud-aware Collectives forML Workloads with Rank Reordering
- Augmenting Anchors by the Detector Itself
- Support vector machines and linear regression coincide with very high-dimensional features
- Rethinking Noisy Label Models: Labeler-Dependent Noise with Adversarial Awareness
- Bhasacitra: Visualising the dialect geography of South Asia
- UCPhrase: Unsupervised Context-aware Quality Phrase Tagging
- On the Bias Against Inductive Biases
- Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning
- Classification of Brain Tumours in MR Images using Deep Spatiospatial Models
- Accelerating Neural ODEs Using Model Order Reduction
- The Evaluation of Rating Systems in Team-based Battle Royale Games
- TransCamP: Graph Transformer for 6-DoF Camera Pose Estimation
- Controllable Abstractive Dialogue Summarization with Sketch Supervision
- Symmetry-driven graph neural networks
- Targeted Deep Learning: Framework, Methods, and Applications
- Fair Representations by Compression
- Towards mental time travel: a hierarchical memory for reinforcement learning agents
- Learning to Extend Program Graphs to Work-in-Progress Code
- DeepMoM: Robust Deep Learning With Median-of-Means
- An Inexact Projected Gradient Method with Rounding and Lifting by Nonlinear Programming for Solving Rank-One Semidefinite Relaxation of Polynomial Optimization
- The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider
- Near-Optimal Multi-Perturbation Experimental Design for Causal Structure Learning
- Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging
- Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model
- Feature extraction and evaluation for BioMedical Question Answering
- Iris Liveness Detection using a Cascade of Dedicated Deep Learning Networks
- Online Hate: Behavioural Dynamics and Relationship with Misinformation
- What if This Modified That? Syntactic Interventions via Counterfactual Embeddings
- On Hamilton-Jacobi PDEs and image denoising models with certain non-additive noise
- SemEval-2021 Task 9: Fact Verification and Evidence Finding for Tabular Data in Scientific Documents (SEM-TAB-FACTS)
- Linguistic Structures as Weak Supervision for Visual Scene Graph Generation
- PTNet: A High-Resolution Infant MRI Synthesizer Based on Transformer
- Improving Generalization in Mountain Car Through the Partitioned Parameterized Policy Approach via Quasi-Stochastic Gradient Descent
- Confident in the Crowd: Bayesian Inference to Improve Data Labelling in Crowdsourcing
- EDEN: Deep Feature Distribution Pooling for Saimaa Ringed Seals Pattern Matching
- What Is Considered Complete for Visual Recognition?
- Perturbation Theory for the Information Bottleneck
- Relation Matters in Sampling: A Scalable Multi-Relational Graph Neural Network for Drug-Drug Interaction Prediction
- Bridging Data Center AI Systems with Edge Computing for Actionable Information Retrieval
- Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation
- NViSII: A Scriptable Tool for Photorealistic Image Generation
- Cisco at SemEval-2021 Task 5: What's Toxic?: Leveraging Transformers for Multiple Toxic Span Extraction from Online Comments
- A Gradient Method for Multilevel Optimization
- Latent Space Exploration Using Generative Kernel PCA
- Changing the World by Changing the Data
- Quantum Optimisation of Complex Systems with a Quantum Annealer
- Towards Deterministic Diverse Subset Sampling
- Efficient Online-Bandit Strategies for Minimax Learning Problems
- Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks
- Quantifying and Localizing Usable Information Leakage from Neural Network Gradients
- Geometric Deep Learning and Equivariant Neural Networks
- Discretization Drift in Two-Player Games
- Scalable Frank-Wolfe on Generalized Self-concordant Functions via Simple Steps
- Training of SSD(Single Shot Detector) for Facial Detection using Nvidia Jetson Nano
- Demotivate adversarial defense in remote sensing
- Video-rate multispectral imaging in laparoscopic surgery: First-in-human application
All 181
- Volatility Modeling of Stocks from Selected Sectors of the Indian Economy Using GARCH
- Equilibrium and non-Equilibrium regimes in the learning of Restricted Boltzmann Machines
- Knowledge Inheritance for Pre-trained Language Models
- Learning Relation Alignment for Calibrated Cross-modal Retrieval
- Recursive Contour Saliency Blending Network for Accurate Salient Object Detection
- Generative Network-Based Reduced-Order Model for Prediction, Data Assimilation and Uncertainty Quantification
- Learning Approximate and Exact Numeral Systems via Reinforcement Learning
- Lightweight Cross-Lingual Sentence Representation Learning
- Neonatal seizure detection from raw multi-channel EEG using a fully convolutional architecture
- pRSL: Interpretable Multi-label Stacking by Learning Probabilistic Rules
- A General Taylor Framework for Unifying and Revisiting Attribution Methods
- Implicit Regularization in Matrix Sensing via Mirror Descent
- Improving Facial Attribute Recognition by Group and Graph Learning
- Language Models Use Monotonicity to Assess NPI Licensing
- A proxemics game between festival visitors and an industrial robot
- A Survey on Anomaly Detection for Technical Systems using LSTM Networks
- The Herbarium 2021 Half-Earth Challenge Dataset
- DIVE: End-to-end Speech Diarization via Iterative Speaker Embedding
- A Probabilistic Forecast-Driven Strategy for a Risk-Aware Participation in the Capacity Firming Market: extended version
- GCN-SL: Graph Convolutional Networks with Structure Learning for Graphs under Heterophily
- The Wits Intelligent Teaching System: Detecting Student Engagement During Lectures Using Convolutional Neural Networks
- A systematic review of transfer learning based approaches for diabetic retinopathy detection
- Early Exiting with Ensemble Internal Classifiers
- Using Convolutional Neural Networks for Relative Pose Estimation of a Non-Cooperative Spacecraft with Thermal Infrared Imagery
- Do not explain without context: addressing the blind spot of model explanations
- How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation
- Chromatic and spatial analysis of one-pixel attacks against an image classifier
- The Feature-First Block Model
- New Encoder Learning for Captioning Heavy Rain Images via Semantic Visual Feature Matching
- SafeAMC: Adversarial training for robust modulation recognition models
- Robust Regularization with Adversarial Labelling of Perturbed Samples
- DeepTag: A General Framework for Fiducial Marker Design and Detection
- An Explanatory Query-Based Framework for Exploring Academic Expertise
- Slow Momentum with Fast Reversion: A Trading Strategy Using Deep Learning and Changepoint Detection
- OTTers: One-turn Topic Transitions for Open-Domain Dialogue
- Natural Language Processing 4 All (NLP4All): A New Online Platform for Teaching and Learning NLP Concepts
- Fair and Adventurous Enumeration of Quantifier Instantiations
- Network Activities Recognition and Analysis Based on Supervised Machine Learning Classification Methods Using J48 and Na"ive Bayes Algorithm
- AutoSampling: Search for Effective Data Sampling Schedules
- Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving
- Focus on Local: Detecting Lane Marker from Bottom Up via Key Point
- ResT: An Efficient Transformer for Visual Recognition
- Measuring global properties of neural generative model outputs via generating mathematical objects
- Domain-Adaptive Pretraining Methods for Dialogue Understanding
- Inside ASCENT: Exploring a Deep Commonsense Knowledge Base and its Usage in Question Answering
- Deception Detection in Videos using the Facial Action Coding System
- Scheduling Jobs with Stochastic Holding Costs
- Data Augmentation for Text Generation Without Any Augmented Data
- Pruning and Slicing Neural Networks using Formal Verification
- Cross-Lingual Abstractive Summarization with Limited Parallel Resources
- Learning to Select Cuts for Efficient Mixed-Integer Programming
- The Power of Sampling: Dimension-free Risk Bounds in Private ERM
- The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization
- Noised Consistency Training for Text Summarization
- THINK: A Novel Conversation Model for Generating Grammatically Correct and Coherent Responses
- ByT5: Towards a token-free future with pre-trained byte-to-byte models
- Enhanced Doubly Robust Learning for Debiasing Post-click Conversion Rate Estimation
- CRT-Net: A Generalized and Scalable Framework for the Computer-Aided Diagnosis of Electrocardiogram Signals
- Optimal Model Placement and Online Model Splitting for Device-Edge Co-Inference
- A nearly Blackwell-optimal policy gradient method
- Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax
- Alleviating the Knowledge-Language Inconsistency: A Study for Deep Commonsense Knowledge
- Short-Term Stock Price-Trend Prediction Using Meta-Learning
- Semi-supervised Anatomical Landmark Detection via Shape-regulated Self-training
- Spatio-Temporal Dual Graph Neural Networks for Travel Time Estimation
- Information Fragmentation, Encryption and Information Flow in Complex Biological Networks
- MODISSA: a multipurpose platform for the prototypical realization of vehicle-related applications using optical sensors
- Hierarchical Transformer Encoders for Vietnamese Spelling Correction
- 2nd Place Solution for IJCAI-PRICAI 2020 3D AI Challenge: 3D Object Reconstruction from A Single Image
- Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translation
- Predicting the hosts of prokaryotic viruses using GCN-based semi-supervised learning
- ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation
- One-shot Learning with Absolute Generalization
- Self-supervised Detransformation Autoencoder for Representation Learning in Open Set Recognition
- Blending Advertising with Organic Content in E-Commerce: A Virtual Bids Optimization Approach
- A Machine Learning and Computer Vision Approach to Rapidly Optimize Multiscale Droplet Generation
- ECG Heart-beat Classification Using Multimodal Image Fusion
- Inertial Sensor Data To Image Encoding For Human Action Recognition
- Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task
- Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture
- Stochastic Intervention for Causal Inference via Reinforcement Learning