Papers
Mon 31 May 2021
214 papers
- On Fast Sampling of Diffusion Probabilistic ModelsDiffusion models → Diffusion foundations and sampling
- Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPsOffline RL and imitation learning from data → Safe offline RL
- M6-T: Exploring Sparse Expert Models and BeyondMixture-of-experts → Efficient MoE training and inference systems
- Greedy-layer Pruning: Speeding up Transformer Models for Natural Language ProcessingKnowledge distillation → Knowledge distillation for LLMs
- Explainability via Interactivity? Supporting Nonexperts' Sensemaking of Pretrained CNN by Interacting with Their Daily Surroundings
- WiCluster: Passive Indoor 2D/3D Positioning using WiFi without Precise Labels
- A Bytecode-based Approach for Smart Contract Classification
- Similarity Embedding Networks for Robust Human Activity Recognition
- A keyword-driven approach to science
- Know Your Model (KYM): Increasing Trust in AI and Machine Learning
- Data Fusion for Deep Learning on Transport Mode Detection: A Case Study
- Online Bayesian inference for multiple changepoints and risk assessment
- Analysis of convolutional neural network image classifiers in a hierarchical max-pooling model with additional local pooling
- An ordinal CNN approach for the assessment of neurological damage in Parkinson's disease patients
- Byakto Speech: Real-time long speech synthesis with convolutional neural network: Transfer learning from English to Bangla
- Multi-Objectivizing Software Configuration Tuning (for a single performance concern)
- Neural message passing for joint paratope-epitope prediction
- Meta-HAR: Federated Representation Learning for Human Activity Recognition
- Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests
- Dynamic Scheduling for Over-the-Air Federated Edge Learning with Energy Constraints
- Federated Estimation of Causal Effects from Observational Data
- HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalization
- Corpus-Based Paraphrase Detection Experiments and Review
- An Exploratory Analysis of Multilingual Word-Level Quality Estimation with Cross-Lingual Transformers
- Training ELECTRA Augmented with Multi-word Selection
- Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
- GANs Can Play Lottery Tickets Too
- AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning
- Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelation
- Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents
- Deep Reinforcement Learning in Quantitative Algorithmic Trading: A Review
- Probabilistic Deep Learning with Probabilistic Neural Networks and Deep Probabilistic Models
- Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images
- Fine-grained Generalization Analysis of Structured Output Prediction
- A Methodology for Exploring Deep Convolutional Features in Relation to Hand-Crafted Features with an Application to Music Audio Modeling
- 3D map creation using crowdsourced GNSS data
- The kernel perspective on dynamic mode decomposition
- Text Summarization with Latent Queries
- Control Occupation Kernel Regression for Nonlinear Control-Affine Systems
- Generalized AdaGrad (G-AdaGrad) and Adam: A State-Space Perspective
- Deep learning for prediction of hepatocellular carcinoma recurrence after resection or liver transplantation: a discovery and validation study
- Node-Variant Graph Filters in Graph Neural Networks
- Language Model Evaluation Beyond Perplexity
- Automating Visualization Quality Assessment: a Case Study in Higher Education
- Closer Look at the Uncertainty Estimation in Semantic Segmentation under Distributional Shift
- Variational Combinatorial Sequential Monte Carlo Methods for Bayesian Phylogenetic Inference
- GRAVITAS: Graphical Reticulated Attack Vectors for Internet-of-Things Aggregate Security
- Early Detection of COVID-19 Hotspots Using Spatio-Temporal Data
- Using machine learning for quantum annealing accuracy prediction
- Stable and Interpretable Unrolled Dictionary Learning
- More than just Frequency? Demasking Unsupervised Hypernymy Prediction Methods
- Low-Resource Spoken Language Identification Using Self-Attentive Pooling and Deep 1D Time-Channel Separable Convolutions
- Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
- Learning and Generalization in RNNs
- StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts
- A study on the plasticity of neural networks
- HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture
- Machine-Learning Non-Conservative Dynamics for New-Physics Detection
- Diffusion Self-Organizing Map on the Hypersphere
- Persistent Homology Captures the Generalization of Neural Networks Without A Validation Set
- Deep-Learning Discovers Macroscopic Governing Equations for Viscous Gravity Currents from Microscopic Simulation Data
- Robust discovery of partial differential equations in complex situations
- SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
- A Simple and General Debiased Machine Learning Theorem with Finite Sample Guarantees
- Unifying Distillation with Personalization in Federated Learning
- CVaR-based Flight Energy Risk Assessment for Multirotor UAVs using a Deep Energy Model
- Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization
- Efficient and Modular Implicit Differentiation
- Model Mis-specification and Algorithmic Bias
- How transfer learning impacts linguistic knowledge in deep NLP models?
- Reinforced Generative Adversarial Network for Abstractive Text Summarization
- Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training
- MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens
- DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
- Automatic audiovisual synchronisation for ultrasound tongue imaging
- Adaptive Feature Alignment for Adversarial Training
- Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning
- Policies for the Dynamic Traveling Maintainer Problem with Alerts
- Pho(SC)-CTC -- A Hybrid Approach Towards Zero-shot Word Image Recognition
- Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model
- Beyond Noise: Mitigating the Impact of Fine-grained Semantic Divergences on Neural Machine Translation
- Optimal Spectral Recovery of a Planted Vector in a Subspace
- SA2SL: From Aspect-Based Sentiment Analysis to Social Listening System for Business Intelligence
- Can Attention Enable MLPs To Catch Up With CNNs?
- SDNet: mutil-branch for single image deraining using swin
- Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark
- Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition
- Detecting Fetal Alcohol Spectrum Disorder in children using Artificial Neural Network
- Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data
- On the Consistency of Max-Margin Losses
- Picking Pearl From Seabed: Extracting Artefacts from Noisy Issue Triaging Collaborative Conversations for Hybrid Cloud Services
- Using Pareto Simulated Annealing to Address Algorithmic Bias in Machine Learning
- Dominant Patterns: Critical Features Hidden in Deep Neural Networks
- Telling Stories through Multi-User Dialogue by Modeling Character Relations
- Factorising Meaning and Form for Intent-Preserving Paraphrasing
- Scorpion detection and classification systems based on computer vision and deep learning for health security purposes
- A Novel Automatic Modulation Classification Scheme Based on Multi-Scale Networks
- Machine Learning for Security in Vehicular Networks: A Comprehensive Survey
- A remark on a paper of Krotov and Hopfield [arXiv:2008.06996]
- DiaKG: an Annotated Diabetes Dataset for Medical Knowledge Graph Construction
All 214
- Integrating Contextual Knowledge to Visual Features for Fine Art Classification
- OASIS: An Active Framework for Set Inversion
- Reinforcement Learning-based Dynamic Service Placement in Vehicular Networks
- Neural Bi-Lexicalized PCFG Induction
- Product Progression: a machine learning approach to forecasting industrial upgrading
- SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning
- Large-Scale Data-Driven Airline Market Influence Maximization
- Query Attack by Multi-Identity Surrogates
- Locally Private k-Means Clustering with Constant Multiplicative Approximation and Near-Optimal Additive Error
- Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime
- Choose a Transformer: Fourier or Galerkin
- MAOMaps: A Photo-Realistic Benchmark For vSLAM and Map Merging Quality Assessment
- Urban Traffic Surveillance (UTS): A fully probabilistic 3D tracking approach based on 2D detections
- Representation Learning Beyond Linear Prediction Functions
- Feasibility Assessment of Multitasking in MRI Neuroimaging Analysis: Tissue Segmentation, Cross-Modality Conversion and Bias correction
- Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition
- Privileged Graph Distillation for Cold Start Recommendation
- Non-Convex Tensor Low-Rank Approximation for Infrared Small Target Detection
- OCT-GAN: Neural ODE-based Conditional Tabular GANs
- Boosting the Performance of Video Compression Artifact Reduction with Reference Frame Proposals and Frequency Domain Information
- Conformal Uncertainty Sets for Robust Optimization
- VidFace: A Full-Transformer Solver for Video FaceHallucination with Unaligned Tiny Snapshots
- ACE-NODE: Attentive Co-Evolving Neural Ordinary Differential Equations
- SNIPS: Solving Noisy Inverse Problems Stochastically
- The effectiveness of feature attribution methods and its correlation with automatic evaluation scores
- Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?
- Safe Pontryagin Differentiable Programming
- The use of Generative Adversarial Networks to characterise new physics in multi-lepton final states at the LHC
- First Full-Event Reconstruction from Imaging Atmospheric Cherenkov Telescope Real Data with Deep Learning
- Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker
- Hybrid Henry Gas Solubility Optimization Algorithm with Dynamic Cluster-to-Algorithm Mapping for Search-based Software Engineering Problems
- How Lexical Gold Standards Have Effects On The Usefulness Of Text Analysis Tools For Digital Scholarship
- SMASH: a Semantic-enabled Multi-agent Approach for Self-adaptation of Human-centered IoT
- GWLAN: General Word-Level AutocompletioN for Computer-Aided Translation
- A unified view of likelihood ratio and reparameterization gradients
- Retweet communities reveal the main sources of hate speech
- Connecting Language and Vision for Natural Language-Based Vehicle Retrieval
- LTL-Constrained Steady-State Policy Synthesis
- ACNet: Mask-Aware Attention with Dynamic Context Enhancement for Robust Acne Detection
- Rawlsian Fair Adaptation of Deep Learning Classifiers
- An Exploratory Analysis of the Relation Between Offensive Language and Mental Health
- A Multilingual Modeling Method for Span-Extraction Reading Comprehension
- SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning
- Verdi: Quality Estimation and Error Detection for Bilingual Corpora
- Adaptive Multi-Source Causal Inference
- Fast, Accurate and Interpretable Time Series Classification Through Randomization
- Bangla Natural Language Processing: A Comprehensive Analysis of Classical, Machine Learning, and Deep Learning Based Methods
- Variational Autoencoders: A Harmonic Perspective
- Consistency Regularization for Variational Auto-Encoders
- Learning Free-Form Deformation for 3D Face Reconstruction from In-The-Wild Images
- Cascaded Head-colliding Attention
- Why does CTC result in peaky behavior?
- Refined Deep Neural Network and U-Net for Polyps Segmentation
- Demographic Fairness in Biometric Systems: What do the Experts say?
- Towards Lower Bounds on the Depth of ReLU Neural Networks
- Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation
- Bounded logit attention: Learning to explain image classifiers
- Effective Batching for Recurrent Neural Network Grammars
- An exact counterfactual-example-based approach to tree-ensemble models interpretability
- Supporting Cognitive and Emotional Empathic Writing of Students
- Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models
- Transfer Learning for Sequence Generation: from Single-source to Multi-source
- Scene-aware Generative Network for Human Motion Synthesis
- Gradient-based Data Subversion Attack Against Binary Classifiers
- On Compositional Generalization of Neural Machine Translation
- RED : Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networks
- Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning
- Predicting Driver Intention Using Deep Neural Network
- Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart
- SN-Graph: a Minimalist 3D Object Representation for Classification
- A Semantic-based Method for Unsupervised Commonsense Question Answering
- Procedural Content Generation: Better Benchmarks for Transfer Reinforcement Learning
- Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR
- Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation
- LIIR at SemEval-2021 task 6: Detection of Persuasion Techniques In Texts and Images using CLIP features
- Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction
- Energy-Efficient and Federated Meta-Learning via Projected Stochastic Gradient Ascent
- BaMBNet: A Blur-aware Multi-branch Network for Defocus Deblurring
- Emotional Voice Conversion: Theory, Databases and ESD
- G-Transformer for Document-level Machine Translation
- Low-Dose CT Denoising Using a Structure-Preserving Kernel Prediction Network
- A Protection Method of Trained CNN Model with Secret Key from Unauthorized Access
- Bio-inspired visual attention for silicon retinas based on spiking neural networks applied to pattern classification
- Active Hierarchical Exploration with Stable Subgoal Representation Learning
- Active Learning of Continuous-time Bayesian Networks through Interventions
- A Study On the Effects of Pre-processing On Spatio-temporal Action Recognition Using Spiking Neural Networks Trained with STDP
- Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization
- Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation
- Dual-stream Network for Visual Recognition
- Hierarchical Deep Network with Uncertainty-aware Semi-supervised Learning for Vessel Segmentation
- Transfer Learning as an Enhancement for Reconfiguration Management of Cyber-Physical Production Systems
- Transferable Sparse Adversarial Attack
- 1xN Pattern for Pruning Convolutional Neural Networks
- CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomography
- Robustifying ℓ_∞ Adversarial Training to the Union of Perturbation Models
- The Role of Entropy in Guiding a Connection Prover
- Parkinsonian Chinese Speech Analysis towards Automatic Classification of Parkinson's Disease
- Combining resampling and reweighting for faithful stochastic optimization
- Training Domain-invariant Object Detector Faster with Feature Replay and Slow Learner
- Fully Hyperbolic Neural Networks
- DeepChange: A Large Long-Term Person Re-Identification Benchmark with Clothes Change
- Know Your Surroundings: Panoramic Multi-Object Tracking by Multimodality Collaboration
- Zero-shot Fact Verification by Claim Generation
- Image-to-Video Generation via 3D Facial Dynamics
- Characterization of Generalizability of Spike Timing Dependent Plasticity trained Spiking Neural Networks
- NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labels
- Towards a Federated Learning Framework for Heterogeneous Devices of Internet of Things
- A Minimax Lower Bound for Low-Rank Matrix-Variate Logistic Regression
- Memory-Efficient Differentiable Transformer Architecture Search
- On the Interplay Between Fine-tuning and Composition in Transformers
- Federated Learning for Industrial Internet of Things in Future Industries
- Human-level COVID-19 Diagnosis from Low-dose CT Scans Using a Two-stage Time-distributed Capsule Network
- Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry
- Attention Flows are Shapley Value Explanations