Papers
Fri 1 Apr 2022
162 papers
- Feature Structure Distillation with Centered Kernel Alignment in BERT TransferringKnowledge distillation → Knowledge distillation for LLMs
- End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
- Knowledge distillation with error-correcting transfer learning for wind power predictionKnowledge distillation → General knowledge distillation methods
- Socratic Models: Composing Zero-Shot Multimodal Reasoning with LanguageLLM reasoning → Multimodal reasoning
- Unified and Effective Ensemble Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Rethinking Position Bias Modeling with Knowledge Distillation for CTR PredictionKnowledge distillation → Distillation for recommender systems
- Perception Prioritized Training of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense EmbeddingsKnowledge distillation → Knowledge distillation for LLMs
- Machine Learning and Artificial Intelligence in Circular Economy: A Bibliometric Analysis and Systematic Literature Review
- Physical Deep Learning with Biologically Plausible Training Method
- Syntax-informed Question Answering with Heterogeneous Graph Transformer
- Probabilistic AutoRegressive Neural Networks for Accurate Long-range Forecasting
- COOL, a Context Outlooker, and its Application to Question Answering and other Natural Language Processing Tasks
- On the Adaptation to Concept Drift for CTR Prediction
- Automating Staged Rollout with Reinforcement Learning
- Optimising Communication Overhead in Federated Learning Using NSGA-II
- Deep Q-learning of global optimizer of multiply model parameters for viscoelastic imaging
- Data and Physics Driven Learning Models for Fast MRI -- Fundamentals and Methodologies from CNN, GAN to Attention and Transformers
- Learning to Accelerate by the Methods of Step-size Planning
- Personalized Prediction of Future Lesion Activity and Treatment Effect in Multiple Sclerosis from Baseline MRI
- QuadraLib: A Performant Quadratic Neural Network Library for Architecture Optimization and Design Exploration
- Residual-guided Personalized Speech Synthesis based on Face Image
- Survey of Matrix Completion Algorithms
- Internet-of-Things Architectures for Secure Cyber-Physical Spaces: the VISOR Experience Report
- Matrix Completion with Sparse Noisy Rows
- Bi-directional Loop Closure for Visual SLAM
- FedRecAttack: Model Poisoning Attack to Federated Recommendation
- Analysis of Sparse Subspace Clustering: Experiments and Random Projection
- Identifying Exoplanets with Machine Learning Methods: A Preliminary Study
- CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos
- Efficient Argument Structure Extraction with Transfer Learning and Active Learning
- Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk
- A Reinforcement Learning Approach to Sensing Design in Resource-Constrained Wireless Networked Control Systems
- Testing Feedforward Neural Networks Training Programs
- Assimilation of Satellite Active Fires Data
- Learning Audio-Video Modalities from Image Captions
- Learnable latent embeddings for joint behavioral and neural analysis
- CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation
- Hazard Detection And Avoidance For The Nova-C Lander
- Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes
- Robust Neonatal Face Detection in Real-world Clinical Settings
- Hysteresis-Based RL: Robustifying Reinforcement Learning-based Control Policies via Hybrid Control
- End-to-end multi-talker audio-visual ASR using an active speaker attention module
- Cluster-based ensemble learning for wind power modeling with meteorological wind data
- SIMBAR: Single Image-Based Scene Relighting For Effective Data Augmentation For Automated Driving Vision Tasks
- Application of Dimensional Reduction in Artificial Neural Networks to Improve Emergency Department Triage During Chemical Mass Casualty Incidents
- UNetFormer: A Unified Vision Transformer Model and Pre-Training Framework for 3D Medical Image Segmentation
- Extremely Low-light Image Enhancement with Scene Text Restoration
- TopTemp: Parsing Precipitate Structure from Temper Topology
- Explainable and Interpretable Diabetic Retinopathy Classification Based on Neural-Symbolic Learning
- Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
- On the Importance of Asymmetry for Siamese Representation Learning
- Learning the conditional law: signatures and conditional GANs in filtering and prediction of diffusion processes
- From Statistical to Causal Learning
- Quantized GAN for Complex Music Generation from Dance Videos
- Fast and Automatic Object Registration for Human-Robot Collaboration in Industrial Manufacturing
- Monarch: Expressive Structured Matrices for Efficient and Accurate Training
- Robust and Efficient Aggregation for Distributed Learning
- Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation
- What makes useful auxiliary tasks in reinforcement learning: investigating the effect of the target policy
- DFNet: Enhance Absolute Pose Regression with Direct Feature Matching
- Multi-task RNN-T with Semantic Decoder for Streamable Spoken Language Understanding
- Nowruz at SemEval-2022 Task 7: Tackling Cloze Tests with Transformers and Ordinal Regression
- A Novel Multimodal Approach for Studying the Dynamics of Curiosity in Small Group Learning
- End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation
- Hierarchical model reduction driven by machine learning for parametric advection-diffusion-reaction problems in the presence of noisy data
- Semi-FairVAE: Semi-supervised Fair Representation Learning with Adversarial Variational Autoencoder
- Estimating the Jacobian matrix of an unknown multivariate function from sample values by means of a neural network
- Learning Disentangled Representations of Negation and Uncertainty
- Separate and conquer heuristic allows robust mining of contrast sets in classification, regression, and survival data
- Physics Informed Shallow Machine Learning for Wind Speed Prediction
- A Global Modeling Approach for Load Forecasting in Distribution Networks
- Provable concept learning for interpretable predictions using variational autoencoders
- FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting
- Accelerating Federated Edge Learning via Topology Optimization
- Robust and Accurate -- Compositional Architectures for Randomized Smoothing
- GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval
- Proper Reuse of Image Classification Features Improves Object Detection
- Simulator-based explanation and debugging of hazard-triggering events in DNN-based safety-critical systems
- Autonomous crater detection on asteroids using a fully-convolutional neural network
- Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Models
- Deep Neural Convolutive Matrix Factorization for Articulatory Representation Decomposition
- Evaluation of Fake News Detection with Knowledge-Enhanced Language Models
- Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognition
- Zero-Shot Cross-lingual Aphasia Detection using Automatic Speech Recognition
- Human Evaluation and Correlation with Automatic Metrics in Consultation Note Generation
- Marginal Contrastive Correspondence for Guided Image Generation
- AdaSpeech 4: Adaptive Text to Speech in Zero-Shot Scenarios
- Sense disambiguation of compound constituents
- Comparison of convolutional neural networks for cloudy optical images reconstruction from single or multitemporal joint SAR and optical images
- Transformers for 1D Signals in Parkinson's Disease Detection from Gait
- Oil reservoir recovery factor assessment using Bayesian networks based on advanced approaches to analogues clustering
- Synthetic Photovoltaic and Wind Power Forecasting Data
- Structured Pruning Learns Compact and Accurate Models
- A Semismooth Newton Stochastic Proximal Point Algorithm with Variance Reduction
- CTAB-GAN+: Enhancing Tabular Data Synthesis
- Probing Speech Emotion Recognition Transformers for Linguistic Knowledge
- When to Classify Events in Open Times Series?
- Automatic Biomedical Term Clustering by Learning Fine-grained Term Representations
- DAG-WGAN: Causal Structure Learning With Wasserstein Generative Adversarial Networks
All 162
- Autoencoder for Synthetic to Real Generalization: From Simple to More Complex Scenes
- Autoencoder Attractors for Uncertainty Estimation
- Weakly Supervised Regional and Temporal Learning for Facial Action Unit Recognition
- Deep Page-Level Interest Network in Reinforcement Learning for Ads Allocation
- Few-shot One-class Domain Adaptation Based on Frequency for Iris Presentation Attack Detection
- Learning to Deblur using Light Field Generated and Real Defocus Images
- Extracting Rules from Neural Networks with Partial Interpretations
- RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds
- On the Efficiency of Integrating Self-supervised Learning and Meta-learning for User-defined Few-shot Keyword Spotting
- Revisiting Shallow Discourse Parsing in the PDTB-3: Handling Intra-sentential Implicits
- WavFT: Acoustic model finetuning with labelled and unlabelled data
- Cyberbullying detection across social media platforms via platform-aware adversarial encoding
- PriMock57: A Dataset Of Primary Care Mock Consultations
- DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow
- Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations
- CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection
- Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications
- Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression
- Building Decision Forest via Deep Reinforcement Learning
- Face identification by means of a neural net classifier
- Actual Causality and Responsibility Attribution in Decentralized Partially Observable Markov Decision Processes
- Unitail: Detecting, Reading, and Matching in Retail Scene
- Scalable Semi-Modular Inference with Variational Meta-Posteriors
- GrowliFlower: An image time series dataset for GROWth analysis of cauLIFLOWER
- Preventing Distillation-based Attacks on Neural Network IP
- Text-To-Speech Data Augmentation for Low Resource Speech Recognition
- Predicting Intervention Approval in Clinical Trials through Multi-Document Summarization
- Selecting task with optimal transport self-supervised learning for few-shot classification
- Symbolic Search for Optimal Planning with Expressive Extensions
- i-Razor: A Differentiable Neural Input Razor for Feature Selection and Dimension Search in DNN-Based Recommender Systems
- Fusing Interpretable Knowledge of Neural Network Learning Agents For Swarm-Guidance
- Multifaceted Improvements for Conversational Open-Domain Question Answering
- MS-HLMO: Multi-scale Histogram of Local Main Orientation for Remote Sensing Image Registration
- NC-DRE: Leveraging Non-entity Clue Information for Document-level Relation Extraction
- ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition
- Online panoptic 3D reconstruction as a Linear Assignment Problem
- Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization
- End-to-End Multi-speaker ASR with Independent Vector Analysis
- Federated Learning Framework Coping with Hierarchical Heterogeneity in Cooperative ITS
- Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems
- A Physics-Guided Neural Operator Learning Approach to Model Biological Tissues from Digital Image Correlation Measurements
- LoCoV: low dimension covariance voting algorithm for portfolio optimization
- Graph Enhanced Contrastive Learning for Radiology Findings Summarization
- Epipolar Focus Spectrum: A Novel Light Field Representation and Application in Dense-view Reconstruction
- Comparative Analysis of Interval Reachability for Robust Implicit and Feedforward Neural Networks
- Dynamic Supervisor for Cross-dataset Object Detection
- GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Feature
- Better Intermediates Improve CTC Inference
- Alternate Intermediate Conditioning with Syllable-level and Character-level Targets for Japanese ASR
- InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASR
- A Unified Framework for Domain Adaptive Pose Estimation
- Making Pre-trained Language Models End-to-end Few-shot Learners with Contrastive Prompt Tuning
- Filter-based Discriminative Autoencoders for Children Speech Recognition
- Mutual Scene Synthesis for Mixed Reality Telepresence
- LASER: LAtent SpacE Rendering for 2D Visual Localization
- Stereo Unstructured Magnification: Multiple Homography Image for View Synthesis
- An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection
- DBCal: Density Based Calibration of classifier predictions for uncertainty quantification
- Semi-Weakly Supervised Object Detection by Sampling Pseudo Ground-Truth Boxes
- MyMove: Facilitating Older Adults to Collect In-Situ Activity Labels on a Smartwatch with Speech
- Effect of Balancing Data Using Synthetic Data on the Performance of Machine Learning Classifiers for Intrusion Detection in Computer Networks
- Leveraging Privacy Profiles to Empower Users in the Digital Society