Papers
Fri 29 Oct 2021
159 papers
- Estimating and Maximizing Mutual Information for Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- On Cross-Layer Alignment for Model Fusion of Heterogeneous Neural NetworksKnowledge distillation → General knowledge distillation methods
- Unsupervised Foreground Extraction via Deep Region CompetitionMixture-of-experts → Vision mixture-of-experts
- Towards Tractable Mathematical Reasoning: Challenges, Strategies, and Opportunities for Solving Math Word Problems
- RF-Net: a Unified Meta-learning Framework for RF-enabled One-shot Human Activity Recognition
- Systematic Review for AI-based Language Learning Tools
- Deep Keyphrase Completion
- Learning Circular Hidden Quantum Markov Models: A Tensor Network Approach
- SVBRDF Recovery From a Single Image With Highlights using a Pretrained Generative Adversarial Network
- Turning Traffic Monitoring Cameras into Intelligent Sensors for Traffic Density Estimation
- IRA: A shape matching approach for recognition and comparison of generic atomic patterns
- Predicting Atlantic Multidecadal Variability
- Longitudinal Analysis of Mask and No-Mask on Child Face Recognition
- Visual Explanations for Convolutional Neural Networks via Latent Traversal of Generative Adversarial Networks
- Combining Public and Private Data
- Classification of jujube fruit based on several pricing factors using machine learning methods
- FC2T2: The Fast Continuous Convolutional Taylor Transform with Applications in Vision and Graphics
- High-dimensional multi-trait GWAS by reverse prediction of genotypes
- The Golden Rule as a Heuristic to Measure the Fairness of Texts Using Machine Learning
- Fetal MRI by robust deep generative prior reconstruction and diffeomorphic registration: application to gestational age prediction
- Evaluation of an Anomaly Detector for Routers using Parameterizable Malware in an IoT Ecosystem
- Online Optimization with Feedback Delay and Nonlinear Switching Cost
- Optimal Compression of Locally Differentially Private Mechanisms
- Measuring a Texts Fairness Dimensions Using Machine Learning Based on Social Psychological Factors
- A Scalable AutoML Approach Based on Graph Neural Networks
- Deep Deterministic Uncertainty for Semantic Segmentation
- DeepDoseNet: A Deep Learning model for 3D Dose Prediction in Radiation Therapy
- Generalized Proximal Policy Optimization with Sample Reuse
- ReSkin: versatile, replaceable, lasting tactile skins
- Deep inference of latent dynamics with spatio-temporal super-resolution using selective backpropagation through time
- Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction
- Polyline Generative Navigable Space Segmentation for Autonomous Visual Navigation
- Improving Generalization Bounds for VC Classes Using the Hypergeometric Tail Inversion
- Word embeddings for topic modeling: an application to the estimation of the economic policy uncertainty index
- Generalized Data Weighting via Class-level Gradient Manipulation
- Symbolic Regression via Neural-Guided Genetic Programming Population Seeding
- Diagnosing Data from ICTs to Provide Focused Assistance in Agricultural Adoptions
- On the Power of Edge Independent Graph Models
- Robust and efficient change point detection using novel multivariate rank-energy GoF test
- Multivariate rank via entropic optimal transport: sample efficiency and generative modeling
- CvS: Classification via Segmentation For Small Datasets
- On-device Real-time Hand Gesture Recognition
- Real-Time Detection of Anomalies in Large-Scale Transient Surveys
- Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr"om Method
- Neural Networks as Kernel Learners: The Silent Alignment Effect
- Federated Semi-Supervised Learning with Class Distribution Mismatch
- Reinforced Workload Distribution Fairness
- Domain Agnostic Few-Shot Learning For Document Intelligence
- Adaptive Hierarchical Similarity Metric Learning with Noisy Labels
- Concept and Attribute Reduction Based on Rectangle Theory of Formal Concept
- Granule Description based on Compound Concepts
- A New Algorithm based on Extent Bit-array for Computing Formal Concepts
- Support Recovery with Stochastic Gates: Theory and Application for Linear Models
- Visual Keyword Spotting with Attention
- A deep convolutional neural network for classification of Aedes albopictus mosquitoes
- Limiting fluctuation and trajectorial stability of multilayer neural networks with mean field training
- Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains
- MetaICL: Learning to Learn In Context
- Personalized breath based biometric authentication with wearable multimodality
- Unsupervised Full Constituency Parsing with Neighboring Distribution Divergence
- Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems
- Improving the quality of generative models through Smirnov transformation
- On the use of uncertainty in classifying Aedes Albopictus mosquitoes
- Physics-informed linear regression is competitive with two Machine Learning methods in residential building MPC
- Contrastive prediction strategies for unsupervised segmentation and categorization of phonemes and words
- Learning to Be Cautious
- Transformer Ensembles for Sexism Detection
- Learning Co-segmentation by Segment Swapping for Retrieval and Discovery
- Hyperparameter Tuning is All You Need for LISTA
- Application of 2-D Convolutional Neural Networks for Damage Detection in Steel Frame Structures
- Distributing Deep Learning Hyperparameter Tuning for 3D Medical Image Segmentation
- From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey
- Towards Comparative Physical Interpretation of Spatial Variability Aware Neural Networks: A Summary of Results
- Adaptive Discretization in Online Reinforcement Learning
- Combining Unsupervised and Text Augmented Semi-Supervised Learning for Low Resourced Autoregressive Speech Recognition
- CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
- Holistic Deep Learning
- Resampling Base Distributions of Normalizing Flows
- C-MADA: Unsupervised Cross-Modality Adversarial Domain Adaptation framework for medical Image Segmentation
- Landscape analysis of an improved power method for tensor decomposition
- CVAD: A generic medical anomaly detector based on Cascade VAE
- Properties from Mechanisms: An Equivariance Perspective on Identifiable Representation Learning
- On the Feasibility of Predicting Questions being Forgotten in Stack Overflow
- Convergence of Uncertainty Sampling for Active Learning
- Learning to Communicate with Reinforcement Learning for an Adaptive Traffic Control System
- Comparing Machine Learning-Centered Approaches for Forecasting Language Patterns During Frustration in Early Childhood
- GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily
- Collaborative Pure Exploration in Kernel Bandit
- Adversarial Robustness with Semi-Infinite Constrained Learning
- ε-weakened Robustness of Deep Neural Networks
- How to Leverage Multimodal EHR Data for Better Medical Predictions?
- Mixed Cooperative-Competitive Communication Using Multi-Agent Reinforcement Learning
- Aligned Multi-Task Gaussian Process
- On Structural Parameterizations of the Offensive Alliance Problem
- Barlow Graph Auto-Encoder for Unsupervised Network Embedding
- Scalable Inference in SDEs by Direct Matching of the Fokker-Planck-Kolmogorov Equation
- An Effective Image Restorer: Denoising and Luminance Adjustment for Low-photon-count Imaging
- DeF-DReL: Systematic Deployment of Serverless Functions in Fog and Cloud environments using Deep Reinforcement Learning
- Successor Feature Representations
- Boosting Anomaly Detection Using Unsupervised Diverse Test-Time Augmentation
All 159
- A Protocol for Emotions
- Variational Bayesian Optimistic Sampling
- Fusing ASR Outputs in Joint Training for Speech Emotion Recognition
- Overview of ADoBo 2021: Automatic Detection of Unassimilated Borrowings in the Spanish Press
- False Positive Detection and Prediction Quality Estimation for LiDAR Point Cloud Segmentation
- A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis
- Multi-target tracking for video surveillance using deep affinity network: a brief review
- Improved FRQI on superconducting processors and its restrictions in the NISQ era
- QDCNN: Quantum Dilated Convolutional Neural Network
- 3D-OOCS: Learning Prostate Segmentation with Inductive Bias
- Frame-Capture-Based CSI Recomposition Pertaining to Firmware-Agnostic WiFi Sensing
- Amendable Generation for Dialogue State Tracking
- Scale-Aware Dynamic Network for Continuous-Scale Super-Resolution
- Gabor filter incorporated CNN for compression
- Multi-Task and Multi-Modal Learning for RGB Dynamic Gesture Recognition
- Bayesian Optimal Experimental Design for Simulator Models of Cognition
- Attacking Video Recognition Models with Bullet-Screen Comments
- Path-Enhanced Multi-Relational Question Answering with Knowledge Graph Embeddings
- MentalBERT: Publicly Available Pretrained Language Models for Mental Healthcare
- Unsupervised Person Re-Identification with Wireless Positioning under Weak Scene Labeling
- BiC-Net: Learning Efficient Spatio-Temporal Relation for Text-Video Retrieval
- Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels
- Whole Brain Segmentation with Full Volume Neural Network
- Handshakes AI Research at CASE 2021 Task 1: Exploring different approaches for multilingual tasks
- Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit
- Cause-effect inference through spectral independence in linear dynamical systems: theoretical foundations
- Adaptive Importance Sampling meets Mirror Descent: a Bias-variance tradeoff
- ST-ABN: Visual Explanation Taking into Account Spatio-temporal Information for Video Recognition
- A/B/n Testing with Control in the Presence of Subpopulations
- Understanding the Effect of Stochasticity in Policy Optimization
- Novel View Synthesis from a Single Image via Unsupervised learning
- Unsupervised PET Reconstruction from a Bayesian Perspective
- Exposing Deepfake with Pixel-wise AR and PPG Correlation from Faint Signals
- AI-Powered Semantic Segmentation and Fluid Volume Calculation of Lung CT images in Covid-19 Patients
- Crowd-sensing Enhanced Parking Patrol using Trajectories of Sharing Bikes
- Data-driven Uncertainty Quantification in Computational Human Head Models
- A Comprehensive Study on Learning-Based PE Malware Family Classification Methods
- Latent Cognizance: What Machine Really Learns
- Does Momentum Help? A Sample Complexity Analysis
- Improving Fairness via Federated Learning
- Automatic Hand Sign Recognition: Identify Unusuality through Latent Cognizance
- Optimal prediction for kernel-based semi-functional linear regression
- Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing
- Topological Relational Learning on Graphs
- Deconvolutional Networks on Graph Data
- Pre-training Co-evolutionary Protein Representation via A Pairwise Masked Language Model
- PEDENet: Image Anomaly Localization via Patch Embedding and Density Estimation
- ADDS: Adaptive Differentiable Sampling for Robust Multi-Party Learning
- On Label Shift in Domain Adaptation via Wasserstein Distance
- A Pre-processing Method for Fairness in Ranking
- Doubly Robust Interval Estimation for Optimal Policy Evaluation in Online Learning
- UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Models
- Learning Personal Food Preferences via Food Logs Embedding
- GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL
- DOCKSTRING: easy molecular docking yields better benchmarks for ligand design
- Location-routing Optimisation for Urban Logistics Using Mobile Parcel Locker Based on Hybrid Q-Learning Algorithm
- Cycle-Balanced Representation Learning For Counterfactual Inference
- Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning
- BitTrain: Sparse Bitmap Compression for Memory-Efficient Training on the Edge