Papers
Mon 25 Oct 2021
206 papers
- Multitask Adaptation by Retrospective Exploration with Learned World ModelsWorld models → Latent dynamics models and model-based RL
- Generating Watermarked Adversarial TextsLLM safety and security → Watermarking generated content and models
- CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data PoisoningLLM safety and security → Backdoor and data poisoning attacks
- Instance-Conditional Knowledge Distillation for Object DetectionKnowledge distillation → Detection and dense prediction distillation
- MUSE: Feature Self-Distillation with Mutual Information and Self-InformationKnowledge distillation → General knowledge distillation methods
- Medium Access Control protocol for Collaborative Spectrum Learning in Wireless Networks
- The Invisible COVID-19 Crisis: Post-Traumatic Stress Disorder Risk Among Frontline Physicians Treating COVID-19 Patients
- Addressing Privacy Threats from Machine Learning
- Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots
- Learning Continuous Face Representation with Explicit Functions
- Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance
- Differentiable NAS Framework and Application to Ads CTR Prediction
- HSVI for zs-POSGs using Concavity, Convexity and Lipschitz Properties
- Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders
- Detecting speaking persons in video
- Iterative Rule Extension for Logic Analysis of Data: an MILP-based heuristic to derive interpretable binary classification from large datasets
- Hybrid physics-based and data-driven modeling with calibrated uncertainty for lithium-ion battery degradation diagnosis and prognosis
- CLLD: Contrastive Learning with Label Distance for Text Classification
- Bridging the gap to real-world for network intrusion detection systems with data-centric approach
- An algorithm for the computation of joint Hawkes moments with exponential kernel
- Deep Learning Tools for Audacity: Helping Researchers Expand the Artist's Toolkit
- Exposure of occupations to technologies of the fourth industrial revolution
- EarthGAN: Can we visualize the Earth's mantle convection using a surrogate model?
- Physics informed machine learning with Smoothed Particle Hydrodynamics: Hierarchy of reduced Lagrangian models of turbulence
- History Aware Multimodal Transformer for Vision-and-Language Navigation
- Reconciling Risk Allocation and Prevalence Estimation in Public Health Using Batched Bandits
- Negotiating Networks in Oligopoly Markets for Price-Sensitive Products
- Fast PDE-constrained optimization via self-supervised operator learning
- Emulation of physical processes with Emukit
- Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications
- Uncertainty quantification in non-rigid image registration via stochastic gradient Markov chain Monte Carlo
- Towards Realistic Market Simulations: a Generative Adversarial Networks Approach
- Generative Flows as a General Purpose Solution for Inverse Problems
- The Pareto Frontier of model selection for general Contextual Bandits
- A Variational Graph Autoencoder for Manipulation Action Recognition and Prediction
- Learning Neural Transmittance for Efficient Rendering of Reflectance Fields
- Facial Recognition in Collaborative Learning Videos
- Image Quality Assessment using Contrastive Learning
- On the Second-order Convergence Properties of Random Search Methods
- Memory visualization tool for training neural network
- Pediatric Otoscopy Video Screening with Shift Contrastive Anomaly Detection
- VAC-CNN: A Visual Analytics System for Comparative Studies of Deep Convolutional Neural Networks
- DeepHelp: Deep Learning for Shout Crisis Text Conversations
- Adaptive Weighted Multi-View Clustering
- Decomposed Inductive Procedure Learning
- Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs
- Distributionally Robust Recurrent Decoders with Random Network Distillation
- Variational framework for partially-measured physical system control: examples of vision neuroscience and optical random media
- Identifying and Benchmarking Natural Out-of-Context Prediction Problems
- On Learning Prediction-Focused Mixtures
- Demystifying and Generalizing BinaryConnect
- RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network
- IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning
- Findings from Experiments of On-line Joint Reinforcement Learning of Semantic Parser and Dialogue Manager with real Users
- A Probabilistic Framework for Knowledge Graph Data Augmentation
- Transportation Scenario Planning with Graph Neural Networks
- Nested Graph Neural Networks
- Covariance-Generalized Matching Component Analysis for Data Fusion and Transfer Learning
- Spectral unmixing of Raman microscopic images of single human cells using Independent Component Analysis
- Simultaneous Perturbation Method for Multi-Task Weight Optimization in One-Shot Meta-Learning
- Generalized Multi-Task Learning from Substantially Unlabeled Multi-Source Medical Image Data
- Probabilistic Hierarchical Forecasting with Deep Poisson Mixtures
- Quantum machine learning beyond kernel methods
- Self-supervised similarity search for large scientific datasets
- As if by magic: self-supervised training of deep despeckling networks with MERLIN
- An Embedded System for Image-based Crack Detection by using Fine-Tuning model of Adaptive Structural Learning of Deep Belief Network
- Faster Perturbed Stochastic Gradient Methods for Finding Local Minima
- What Would Jiminy Cricket Do? Towards Agents That Behave Morally
- Detecting Wandering Behavior of People with Dementia
- Learning-Augmented Dynamic Power Management with Multiple States via New Ski Rental Bounds
- Communication-Constrained Distributed Quantile Regression with Optimal Statistical Guarantees
- Diagnosing Errors in Video Relation Detectors
- The Nuts and Bolts of Adopting Transformer in GANs
- Shift of Pairwise Similarities for Data Clustering
- Latent-Insensitive autoencoders for Anomaly Detection
- Parameter Prediction for Unseen Deep Architectures
- Rotation Equivariant Deforestation Segmentation and Driver Classification
- Gophormer: Ego-Graph Transformer for Node Classification
- SciClops: Detecting and Contextualizing Scientific Claims for Assisting Manual Fact-Checking
- Quantum Algorithms and Lower Bounds for Linear Regression with Norm Constraints
- MVT: Multi-view Vision Transformer for 3D Object Recognition
- Which Model to Trust: Assessing the Influence of Models on the Performance of Reinforcement Learning Algorithms for Continuous Control Tasks
- AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning
- Unsupervised Source Separation By Steering Pretrained Music Models
- Evolutionary Optimization of High-Coverage Budgeted Classifiers
- 2nd Place Solution for SODA10M Challenge 2021 -- Continual Detection Track
- Where were my keys? -- Aggregating Spatial-Temporal Instances of Objects for Efficient Retrieval over Long Periods of Time
- Uniformly Conservative Exploration in Reinforcement Learning
- Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups
- Some like it tough: Improving model generalization via progressively increasing the training difficulty
- Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models
- Adaptive Data Debiasing through Bounded Exploration
- Can Q-Learning be Improved with Advice?
- Nonuniform Negative Sampling and Log Odds Correction with Rare Events Data
- Applications and Techniques for Fast Machine Learning in Science
- Neural Flows: Efficient Alternative to Neural ODEs
- Dual Skip Connections Minimize the False Positive Rate of Lung Nodule Detection in CT images
- Paradigm Shift in Language Modeling: Revisiting CNN for Modeling Sanskrit Originated Bengali and Hindi Language
- Applying Regression Conformal Prediction with Nearest Neighbors to time series data
- Fair Enough: Searching for Sufficient Measures of Fairness
All 206
- TAPL: Dynamic Part-based Visual Tracking via Attention-guided Part Localization
- ML-Based Analysis to Identify Speech Features Relevant in Predicting Alzheimer's Disease
- Generating artificial texts as substitution or complement of training data
- Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition
- Gradient-based Quadratic Multiform Separation
- AxoNN: An asynchronous, message-driven parallel framework for extreme-scale deep learning
- Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning
- Neural Relightable Participating Media Rendering
- Optimization-Based GenQSGD for Federated Edge Learning
- Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning
- Generative Residual Attention Network for Disease Detection
- Stochastic Rounding for Image Interpolation and Scan Conversion
- Feasibility Study of Neural ODE and DAE Modules for Power System Dynamic Component Modeling
- MoDeRNN: Towards Fine-grained Motion Details for Spatiotemporal Predictive Learning
- Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks
- Shape and Reflectance Reconstruction in Uncontrolled Environments by Differentiable Rendering
- Event Data Association via Robust Model Fitting for Event-based Object Tracking
- Seeing biodiversity: perspectives in machine learning for wildlife conservation
- Persona Authentication through Generative Dialogue
- Optimal Model Averaging: Towards Personalized Collaborative Learning
- DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction
- Interactive Segmentation via Deep Learning and B-Spline Explicit Active Surfaces
- Normative Epistemology for Lethal Autonomous Weapons Systems
- On quantitative Laplace-type convergence results for some exponential probability measures, with two applications
- On Slowly-varying Non-stationary Bandits
- Revealing unforeseen diagnostic image features with deep learning by detecting cardiovascular diseases from apical four-chamber ultrasounds
- SILT: Self-supervised Lighting Transfer Using Implicit Image Decomposition
- Instance-Dependent Partial Label Learning
- The Efficiency Misnomer
- Anatomical and Diagnostic Bayesian Segmentation in Prostate MRI -Should Different Clinical Objectives Mandate Different Loss Functions?
- DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks
- Employing chunk size adaptation to overcome concept drift
- Actions Speak Louder than Listening: Evaluating Music Style Transfer based on Editing Experience
- Optimal Auction Design for the Gradual Procurement of Strategic Service Provider Agents
- Reconstructing Pruned Filters using Cheap Spatial Transformations
- Self-Consistent Models and Values
- Debiasing Credit Scoring using Evolutionary Algorithms
- Novel coronavirus pneumonia lesion segmentation in CT images
- TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation
- Raw Bayer Pattern Image Synthesis for Computer Vision-oriented Image Signal Processing Pipeline Design
- Restore from Restored: Single-image Inpainting
- Domain Adaptation in Multi-View Embedding for Cross-Modal Video Retrieval
- Learning What to Memorize: Using Intrinsic Motivation to Form Useful Memory in Partially Observable Reinforcement Learning
- Algorithms for the Communication of Samples
- Variational Gaussian Processes: A Functional Analysis View
- Quantum Boosting using Domain-Partitioning Hypotheses
- Dictionary Learning Using Rank-One Atomic Decomposition (ROAD)
- Battling Hateful Content in Indic Languages HASOC '21
- A Deep Reinforcement Learning Approach for Audio-based Navigation and Audio Source Localization in Multi-speaker Environments
- Scientific Machine Learning Benchmarks
- DP-XGBoost: Private Machine Learning at Scale
- Multi-scale Iterative Residuals for Fast and Scalable Stereo Matching
- "So You Think You're Funny?": Rating the Humour Quotient in Standup Comedy
- Contrastive Learning for Neural Topic Model
- SSMF: Shifting Seasonal Matrix Factorization
- Adaptive Gaussian Processes on Graphs via Spectral Graph Wavelets
- Maximum Correntropy Criterion Regression models with tending-to-zero scale parameters
- Highly Efficient Natural Image Matting
- Planning for Risk-Aversion and Expected Value in MDPs
- LAE : Long-tailed Age Estimation
- Practical Galaxy Morphology Tools from Deep Supervised Representation Learning
- Fast Gradient Non-sign Methods
- Learning Stochastic Shortest Path with Linear Function Approximation
- A Distillation Learning Model of Adaptive Structural Deep Belief Network for AffectNet: Facial Expression Image Database
- SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World
- Local Independence Testing for Point Processes
- An Adaptive Structural Learning of Deep Belief Network for Image-based Crack Detection in Concrete Structures Using SDNET2018
- Self-Supervised Knowledge Transfer via Loosely Supervised Auxiliary Tasks
- A Dynamical System Perspective for Lipschitz Neural Networks
- Fine-tuning of Pre-trained Transformers for Hate, Offensive, and Profane Content Detection in English and Marathi
- Automatic Extraction of Road Networks from Satellite Images by using Adaptive Structural Deep Belief Network
- TODSum: Task-Oriented Dialogue Summarization with State Tracking
- Improving Embedded Knowledge Graph Multi-hop Question Answering by introducing Relational Chain Reasoning
- Nearly Tight Convergence Bounds for Semi-discrete Entropic Optimal Transport
- mlr3spatiotempcv: Spatiotemporal resampling methods for machine learning in R
- Mixture-of-Variational-Experts for Continual Learning
- Industrial Scene Text Detection with Refined Feature-attentive Network
- Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise
- ZerO Initialization: Initializing Neural Networks with only Zeros and Ones
- Operator Shifting for Model-based Policy Evaluation
- Review-Based Domain Disentanglement without Duplicate Users or Contexts for Cross-Domain Recommendation
- Bone Marrow Cell Recognition: Training Deep Object Detection with A New Loss Function
- Zero-Shot Dialogue Disentanglement by Self-Supervised Entangled Response Selection
- SgSum: Transforming Multi-document Summarization into Sub-graph Selection
- Kernel density estimation-based sampling for neural network classification
- Deep Learning for UAV-based Object Detection and Tracking: A Survey
- Progressively Select and Reject Pseudo-labelled Samples for Open-Set Domain Adaptation
- Accelerated Almost-Sure Convergence Rates for Nonconvex Stochastic Gradient Descent using Stochastic Learning Rates
- Age and Gender Prediction using Deep CNNs and Transfer Learning
- Recurrent Off-policy Baselines for Memory-based Continuous Control
- Orthogonal variance-based feature selection for intrusion detection systems
- Ultra Light OCR Competition Technical Report
- Accelerate 3D Object Processing via Spectral Layout
- Linear Contextual Bandits with Adversarial Corruptions
- Federated Test-Time Adaptive Face Presentation Attack Detection with Dual-Phase Privacy Preservation
- DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021
- No News is Good News: A Critique of the One Billion Word Benchmark
- Least Square Calibration for Peer Review
- Common Information based Approximate State Representations in Multi-Agent Reinforcement Learning
- Fast Rank-1 NMF for Missing Data with KL Divergence
- QuantifyML: How Good is my Machine Learning Model?
- Complete Agent-driven Model-based System Testing for Autonomous Systems
- Towards Partial Monitoring: It is Always too Soon to Give Up
- Alignment Attention by Matching Key and Query Distributions
- A rank-adaptive higher-order orthogonal iteration algorithm for truncated Tucker decomposition
- Recommender Systems meet Mechanism Design