Papers
Fri 4 Mar 2022
157 papers
- Targeted Data Poisoning Attack on News Recommendation System by Content PerturbationLLM safety and security → Membership inference attacks
- Better Supervisory Signals by Observing Learning PathsKnowledge distillation → General knowledge distillation methods
- Differentiable Control Barrier Functions for Vision-based End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
- Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy OptimizationOffline RL and imitation learning from data → Imitation learning methods
- Training language models to follow instructions with human feedbackLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
- Learning Category-Level Generalizable Object Manipulation Policy via Generative Adversarial Self-Imitation Learning from DemonstrationsOffline RL and imitation learning from data → Robot manipulation imitation learning
- An Efficient Subpopulation-based Membership Inference AttackLLM safety and security → Membership inference attacks
- User-Level Membership Inference Attack against Metric Embedding LearningLLM safety and security → Membership inference attacks
- Visibility-Inspired Models of Touch Sensors for Navigation
- Modeling and Validating Temporal Rules with Semantic Petri-Net for Digital Twins
- Exploration of Various Deep Learning Models for Increased Accuracy in Automatic Polyp Detection
- A Typology for Exploring the Mitigation of Shortcut Behavior
- Adaptive Cross-Layer Attention for Image Restoration
- Mammograms Classification: A Review
- OCR quality affects perceived usefulness of historical newspaper clippings -- a user study
- Quantum Deep Learning for Mutant COVID-19 Strain Prediction
- Water and Sediment Analyse Using Predictive Models
- Keep It Accurate and Robust: An Enhanced Nuclei Analysis Framework
- Plant Species Recognition with Optimized 3D Polynomial Neural Networks and Variably Overlapping Time-Coherent Sliding Window
- Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions
- Geodesic Gramian Denoising Applied to the Images Contaminated With Noise Sampled From Diverse Probability Distributions
- False membership rate control in mixture models
- Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneck
- A Small Gain Analysis of Single Timescale Actor Critic
- A Quality Index Metric and Method for Online Self-Assessment of Autonomous Vehicles Sensory Perception
- Concept-based Explanations for Out-Of-Distribution Detectors
- Online Learning of Reusable Abstract Models for Object Goal Navigation
- Machine Learning Simulates Agent-Based Model Towards Policy
- Style-ERD: Responsive and Coherent Online Motion Style Transfer
- Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning
- Improving the Energy Efficiency and Robustness of tinyML Computer Vision using Log-Gradient Input Images
- Bayesian Optimization Meets Hybrid Zero Dynamics: Safe Parameter Learning for Bipedal Locomotion Control
- UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation
- Building 3D Generative Models from Minimal Data
- A streamable large-scale clinical EEG dataset for Deep Learning
- Structured Pruning is All You Need for Pruning CNNs at Initialization
- Ridges, Neural Networks, and the Radon Transform
- BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation
- Machine Learning for CUDA+MPI Design Rules
- Cellular Segmentation and Composition in Routine Histology Images using Deep Learning
- HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening
- No More Than 6ft Apart: Robust K-Means via Radius Upper Bounds
- Computational Fluid Dynamics and Machine Learning as tools for Optimization of Micromixers geometry
- Learning from Label Proportions by Learning with Label Noise
- Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion
- Behavioural Curves Analysis Using Near-Infrared-Iris Image Sequences
- The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methods
- Ontological Learning from Weak Labels
- AutoDIME: Automatic Design of Interesting Multi-Agent Environments
- Didn't see that coming: a survey on non-verbal social human behavior forecasting
- Cooperative Task and Motion Planning for Multi-Arm Assembly Systems
- Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning Algorithms
- Interpretable Off-Policy Learning via Hyperbox Search
- Graph clustering with Boltzmann machines
- From Simultaneous to Streaming Machine Translation by Leveraging Streaming History
- Continuous Rating as Reliable Human Evaluation of Simultaneous Speech Translation
- Real-Time Hybrid Mapping of Populated Indoor Scenes using a Low-Cost Monocular UAV
- Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression
- AutoMap: Automatic Medical Code Mapping for Clinical Prediction Model Deployment
- SFPN: Synthetic FPN for Object Detection
- The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights
- Improving textitTug-of-War sketch using Control-Variates method
- Rethinking Efficient Lane Detection via Curve Modeling
- Characterizing Renal Structures with 3D Block Aggregate Transformers
- R-GCN: The R Could Stand for Random
- Quantum Approximate Optimization Algorithm for Bayesian network structure learning
- Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box
- Mobile authentication of copy detection patterns
- iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform
- Beyond Plain Toxic: Detection of Inappropriate Statements on Flammable Topics for the Russian Language
- Simultaneous Alignment and Surface Regression Using Hybrid 2D-3D Networks for 3D Coherent Layer Segmentation of Retina OCT Images
- MM-DFN: Multimodal Dynamic Fusion Network for Emotion Recognition in Conversations
- AutoMO-Mixer: An automated multi-objective Mixer model for balanced, safe and robust prediction in medicine
- Distributed Methods with Absolute Compression and Error Compensation
- Exploring Scalable, Distributed Real-Time Anomaly Detection for Bridge Health Monitoring
- DiT: Self-supervised Pre-training for Document Image Transformer
- Boosting the Performance of Quantum Annealers using Machine Learning
- ViT-P: Rethinking Data-efficient Vision Transformers from Locality
- Computer-Aided Road Inspection: Systems and Algorithms
- Uncertainty Estimation for Heatmap-based Landmark Localization
- Differentiable Causal Discovery Under Latent Interventions
- F2DNet: Fast Focal Detection Network for Pedestrian Detection
- Adaptive Semi-Supervised Inference for Optimal Treatment Decisions with Electronic Medical Record Data
- Quantum Levenberg--Marquardt Algorithm for optimization in Bundle Adjustment
- Mixed Reality Depth Contour Occlusion Using Binocular Similarity Matching and Three-dimensional Contour Optimisation
- Evaluating Local Model-Agnostic Explanations of Learning to Rank Models with Decision Paths
- Freeform Body Motion Generation from Speech
- Integrating Statistical Uncertainty into Neural Network-Based Speech Enhancement
- Semi-parametric Makeup Transfer via Semantic-aware Correspondence
- Feature Transformation for Cross-domain Few-shot Remote Sensing Scene Classification
- Do Explanations Explain? Model Knows Best
- Class-Aware Contrastive Semi-Supervised Learning
- Patch Similarity Aware Data-Free Quantization for Vision Transformers
- Detecting GAN-generated Images by Orthogonal Training of Multiple CNNs
- IISERB Brains at SemEval 2022 Task 6: A Deep-learning Framework to Identify Intended Sarcasm in English
- OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation
- Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learning
- Improving Ant Colony Optimization Efficiency for Solving Large TSP Instances
- Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration
- ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification
All 157
- Quantification of emotions in decision making
- Look&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement
- Forms and Norms of Indecision in Argumentation Theory
- Evaluating Object (mis)Detection from a Safety and Reliability Perspective: Discussion and Measures
- Sharper Bounds for Proximal Gradient Algorithms with Errors
- Carbon Footprint of Selecting and Training Deep Learning Models for Medical Image Analysis
- Neural Simulated Annealing
- Aggregate effects of advertising decisions: a complex systems look at search engine advertising via an experimental study
- Voice-Face Homogeneity Tells Deepfake
- Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection
- Time-to-Label: Temporal Consistency for Self-Supervised Monocular 3D Object Detection
- Optimal Keywords Grouping in Sponsored Search Advertising under Uncertain Environments
- Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning
- EAG: Extract and Generate Multi-way Aligned Corpus for Complete Multi-lingual Neural Machine Translation
- Passive and Active Learning of Driver Behavior from Electric Vehicles
- GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation
- Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels
- SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models
- Convolutional Analysis Operator Learning by End-To-End Training of Iterative Neural Networks
- MF-Hovernet: An Extension of Hovernet for Colon Nuclei Identification and Counting (CoNiC) Challenge
- Transformations in Learned Image Compression from a Modulation Perspective
- DetFlowTrack: 3D Multi-object Tracking based on Simultaneous Optimization of Object Detection and Scene Flow Estimation
- PatchMVSNet: Patch-wise Unsupervised Multi-View Stereo for Weakly-Textured Surface Reconstruction
- Time-aware Graph Neural Networks for Entity Alignment between Temporal Knowledge Graphs
- HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging
- Attention Concatenation Volume for Accurate and Efficient Stereo Matching
- Whiplash Gradient Descent Dynamics
- Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation
- A Versatile Multi-View Framework for LiDAR-based 3D Object Detection with Guidance from Panoptic Segmentation
- 3D endoscopic depth estimation using 3D surface-aware constraints
- Distributionally Robust Bayesian Optimization with varphi-divergences
- Abuse and Fraud Detection in Streaming Services Using Heuristic-Aware Machine Learning
- Detecting Offensive Language on Social Networks: An End-to-end Detection Method based on Graph Attention Networks
- Adversarial Patterns: Building Robust Android Malware Classifiers
- GraspARL: Dynamic Grasping via Adversarial Reinforcement Learning
- In the Service of Online Order: Tackling Cyber-Bullying with Machine Learning and Affect Analysis
- Towards Benchmarking and Evaluating Deepfake Detection
- MixCL: Pixel label matters to contrastive learning
- FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context
- Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving
- FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosis
- Continual Horizontal Federated Learning for Heterogeneous Data
- Scribble-Supervised Medical Image Segmentation via Dual-Branch Network and Dynamically Mixed Pseudo Labels Supervision
- Interactive Image Synthesis with Panoptic Layout Generation
- Learning Incrementally to Segment Multiple Organs in a CT Image
- Universal Segmentation of 33 Anatomies
- Contrastive Graph Convolutional Networks for Hardware Trojan Detection in Third Party IP Cores
- LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models
- Deep Lexical Hypothesis: Identifying personality structure in natural language
- Teaching Robots to Span the Space of Functional Expressive Motion
- Bayesian community detection for networks with covariates
- Second-order Symmetric Non-negative Latent Factor Analysis
- WPNAS: Neural Architecture Search by jointly using Weight Sharing and Predictor
- Dynamic Backdoors with Global Average Pooling
- Differentially Private Label Protection in Split Learning
- X2T: Training an X-to-Text Typing Interface with Online Learning from User Feedback
- On the relevance of language in speaker recognition