Papers
Sun 12 Sep 2021
97 papers
- On the Efficiency of Subclass Knowledge Distillation in Classification TasksKnowledge distillation → General knowledge distillation methods
- Federated Ensemble Model-based Reinforcement Learning in Edge ComputingKnowledge distillation → Federated, robust and private distillation
- Encoding Distributional Soft Actor-Critic for Autonomous Driving in Multi-lane ScenariosEnd-to-end autonomous driving → Reinforcement learning for driving
- Learning Selective Communication for Multi-Agent Path FindingOffline RL and imitation learning from data → Imitation learning methods
- FLiText: A Faster and Lighter Semi-Supervised Text Classification with Convolution Networks
- FaxPlainAC: A Fact-Checking Tool Based on EXPLAINable Models with HumAn Correction in the Loop
- Algebraic Semantics of Generalized RIFs
- Application of Video-to-Video Translation Networks to Computational Fluid Dynamics
- Predicting Users' Value Changes by the Friends' Influence from Social Media Usage
- Ethics of AI: A Systematic Literature Review of Principles and Challenges
- Domain Adaptation by Maximizing Population Correlation with Neural Architecture Search
- CropDefender: deep watermark which is more convenient to train and more robust against cropping
- On the Impact of Spurious Correlation for Out-of-distribution Detection
- Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?
- Mixing between the Cross Entropy and the Expectation Loss Terms
- Generating Datasets of 3D Garments with Sewing Patterns
- AdViCE: Aggregated Visual Counterfactual Explanations for Machine Learning Model Validation
- Differential Diagnosis of Frontotemporal Dementia and Alzheimer's Disease using Generative Adversarial Network
- Nimber-Preserving Reductions and Homomorphic Sprague-Grundy Game Encodings
- RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models
- MSGDD-cGAN: Multi-Scale Gradients Dual Discriminator Conditional Generative Adversarial Network
- Critical Learning Periods in Federated Learning
- FedTriNet: A Pseudo Labeling Method with Three Players for Federated Semi-supervised Learning
- Levenshtein Training for Word-level Quality Estimation
- Direct Random Search for Fine Tuning of Deep Reinforcement Learning Policies
- Good-Enough Example Extrapolation
- Neural network based order parameter for phase transitions and its applications in high-entropy alloys
- Detecting Handwritten Mathematical Terms with Sensor Based Data
- Multiresolution Deep Implicit Functions for 3D Shape Representation
- U-Net Convolutional Network for Recognition of Vessels and Materials in Chemistry Lab
- Automatic Componentwise Boosting: An Interpretable AutoML System
- Data Analytics for Smart cities: Challenges and Promises
- A Joint Graph and Image Convolution Network for Automatic Brain Tumor Segmentation
- Kernel PCA with the Nystr"om method
- MovieCuts: A New Dataset and Benchmark for Cut Type Recognition
- PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds
- SphereFace Revived: Unifying Hyperspherical Face Recognition
- CoG: a Two-View Co-training Framework for Defending Adversarial Attacks on Graph
- No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets
- Towards a variational Jordan-Lee-Preskill quantum algorithm
- Improved Algorithms for Misspecified Linear Markov Decision Processes
- Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification
- BioLCNet: Reward-modulated Locally Connected Spiking Neural Networks
- Link Scheduling using Graph Neural Networks
- Adversarial Representation Learning With Closed-Form Solvers
- DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval
- Estimating a new panel MSK dataset for comparative analyses of national absorptive capacity systems, economic growth, and development in low and middle income economies
- Extracting Event Temporal Relations via Hyperbolic Geometry
- An Unsupervised Deep-Learning Method for Fingerprint Classification: the CCAE Network and the Hybrid Clustering Strategy
- A Decidability-Based Loss Function
- Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval
- TEASEL: A Transformer-Based Speech-Prefixed Language Model
- Towards Robust Monocular Visual Odometry for Flying Robots on Planetary Missions
- Check Your Other Door! Creating Backdoor Attacks in the Frequency Domain
- A Complex Constrained Total Variation Image Denoising Algorithm with Application to Phase Retrieval
- Unsupervised Domain Adaptation Schemes for Building ASR in Low-resource Languages
- LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection
- DynSTGAT: Dynamic Spatial-Temporal Graph Attention Network for Traffic Signal Control
- HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation
- Illuminating Diverse Neural Cellular Automata for Level Generation
- ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis
- Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation
- A Socially Aware Reinforcement Learning Agent for The Single Track Road Problem
- Facial Anatomical Landmark Detection using Regularized Transfer Learning with Application to Fetal Alcohol Syndrome Recognition
- Efficient Re-parameterization Residual Attention Network For Nonhomogeneous Image Dehazing
- Single-Read Reconstruction for DNA Data Storage Using Transformers
- Stylistic Retrieval-based Dialogue System with Unparallel Training Data
- Exploring Task Difficulty for Few-Shot Relation Extraction
- Compute and Energy Consumption Trends in Deep Learning Inference
- DRo: A data-scarce mechanism to revolutionize the performance of Deep Learning based Security Systems
- Feature Importance in Gradient Boosting Trees with Cross-Validation Feature Selection
- Graph Attention Network Based Single-Pixel Compressive Direction of Arrival Estimation
- Logic Traps in Evaluating Attribution Scores
- Accurate Prediction Using Triangular Type-2 Fuzzy Linear Regression
- End-to-End Conversational Search for Online Shopping with Utterance Transfer
- What happens in Face during a facial expression? Using data mining techniques to analyze facial expression motion vectors
- CAN3D: Fast 3D Medical Image Segmentation via Compact Context Aggregation
- Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception
- Concave Utility Reinforcement Learning with Zero-Constraint Violations
- "Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding
- Multi-Objective Optimization of ReRAM Crossbars for Robust DNN Inferencing under Stochastic Noise
- Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search
- Prioritized Subnet Sampling for Resource-Adaptive Supernet Training
- EMVLight: A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles
- Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classification
- Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration
- Pairwise Supervised Contrastive Learning of Sentence Representations
- Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?
- Cost-Effective Federated Learning in Mobile Edge Networks
- Team NeuroPoly: Description of the Pipelines for the MICCAI 2021 MS New Lesions Segmentation Challenge
- On the Fundamental Limits of Matrix Completion: Leveraging Hierarchical Similarity Graphs
- Guiding Topic Flows in the Generative Chatbot by Enhancing the ConceptNet with the Conversation Corpora
- Differentially Private Variable Selection via the Knockoff Filter
- Challenges and Solutions in DeepFakes
- Leveraging Table Content for Zero-shot Text-to-SQL with Meta-Learning
- Gradients and Subgradients of Buffered Failure Probability
- Spike2Vec: An Efficient and Scalable Embedding Approach for COVID-19 Spike Sequences