Papers
Thu 2 Dec 2021
222 papers
- A Fast Knowledge Distillation Framework for Visual RecognitionKnowledge distillation → General knowledge distillation methods
- The Surprising Effectiveness of Representation Learning for Visual ImitationOffline RL and imitation learning from data → Robot manipulation imitation learning
- Multi-task Self-distillation for Graph-based Semi-Supervised LearningKnowledge distillation → Graph neural network distillation
- A Mixture of Expert Based Deep Neural Network for Improved ASRMixture-of-experts → Multimodal MoE models
- Quantile Filtered Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Predicting infections in the Covid-19 pandemic -- lessons learned
- Equal Bits: Enforcing Equally Distributed Binary Network Weights
- Differentiable Generalised Predictive Coding
- RafterNet: Probabilistic predictions in multi-response regression
- Convergence Guarantees for Deep Epsilon Greedy Policy Learning
- Unsupervised Law Article Mining based on Deep Pre-Trained Language Representation Models with Application to the Italian Civil Code
- Transfer Learning in Conversational Analysis through Reusing Preprocessing Data as Supervisors
- Investigating the Impact of 9/11 on The Simpsons through Natural Language Processing
- Improving the Reliability of Network Intrusion Detection Systems through Dataset Integration
- Optimization of phase-only holograms calculated with scaled diffraction calculation through deep neural networks
- Bio-inspired Polarization Event Camera
- Multi-Content Complementation Network for Salient Object Detection in Optical Remote Sensing Images
- Probabilistic Contrastive Loss for Self-Supervised Learning
- Hamiltonian latent operators for content and motion disentanglement in image sequences
- MultiVerS: Improving scientific claim verification with weak supervision and full-document context
- AdaSplit: Adaptive Trade-offs for Resource-constrained Distributed Deep Learning
- Engineering AI Tools for Systematic and Scalable Quality Assessment in Magnetic Resonance Imaging
- High-Precision Inversion of Dynamic Radiography Using Hydrodynamic Features
- Sample-Efficient Generation of Novel Photo-acid Generator Molecules using a Deep Generative Model
- Label noise detection under the Noise at Random model with ensemble filters
- Evaluator for Emotionally Consistent Chatbots
- Recovering H"older smooth functions from noisy modulo samples
- Probabilistic Tracking with Deep Factors
- Neurosymbolic Systems of Perception & Cognition: The Role of Attention
- Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?
- Online Search With Best-Price and Query-Based Predictions
- PLSUM: Generating PT-BR Wikipedia by Summarizing Multiple Websites
- InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation
- Improving accuracy and uncertainty quantification of deep learning based quantitative MRI using Monte Carlo dropout
- HMC with Normalizing Flows
- Differentially Private Exploration in Reinforcement Learning with Linear Representation
- The Representation Jensen-R'enyi Divergence
- LeapfrogLayers: A Trainable Framework for Effective Topological Sampling
- Fast Neural Representations for Direct Volume Rendering
- Invariant Priors for Bayesian Quadrature
- Scheduling to Learn In An Unsupervised Online Streaming Model
- Towards Interactive Reinforcement Learning with Intrinsic Feedback
- Dimension-Free Average Treatment Effect Inference with Deep Neural Networks
- FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization
- Trajectory Clustering Performance Evaluation: If we know the answer, it's not clustering
- Theoretical Analysis of an XGBoost Framework for Product Cannibalization
- A Generic Graph Sparsification Framework using Deep Reinforcement Learning
- Is Approximation Universally Defensive Against Adversarial Attacks in Deep Neural Networks?
- Neural Head Avatars from Monocular RGB Videos
- D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding
- Improving mathematical questioning in teacher training
- Robust End-to-End Focal Liver Lesion Detection using Unregistered Multiphase Computed Tomography Images
- StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions
- BEVT: BERT Pretraining of Video Transformers
- Masked-attention Mask Transformer for Universal Image Segmentation
- MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
- Co-domain Symmetry for Complex-Valued Deep Learning
- GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras
- Learning Neural Light Fields with Ray-Space Embedding Networks
- Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks
- Object-aware Monocular Depth Prediction with Instance Convolutions
- Recognizing Scenes from Novel Viewpoints
- DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting
- Efficient Neural Radiance Fields for Interactive Free-viewpoint Video
- TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation
- Self-supervised Video Transformer
- OW-DETR: Open-world Detection Transformer
- Sample Complexity of Robust Reinforcement Learning with a Generative Model
- Neural Weight Step Video Compression
- Machine Learning-Based Classification Algorithms for the Prediction of Coronary Heart Diseases
- Dimensions of Motion: Monocular Prediction through Flow Subspaces
- ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction
- Safe Reinforcement Learning for Grid Voltage Control
- Learning Spatial-Temporal Graphs for Active Speaker Detection
- Why Calibration Error is Wrong Given Model Uncertainty: Using Posterior Predictive Checks with Deep Learning
- KPDrop: Improving Absent Keyphrase Generation
- A Hybrid Science-Guided Machine Learning Approach for Modeling and Optimizing Chemical Processes
- Neural Point Light Fields
- Zero-Shot Text-Guided Object Generation with Dream Fields
- Altering Facial Expression Based on Textual Emotion
- Target Propagation via Regularized Inversion
- Indexed Minimum Empirical Divergence for Unimodal Bandits
- Architecting and Visualizing Deep Reinforcement Learning Models
- Hydroclimatic time series features at multiple time scales
- Learning Large-scale Network Embedding from Representative Subgraph
- A Review of SHACL: From Data Validation to Schema Reasoning for RDF Graphs
- Level set learning with pseudo-reversible neural networks for nonlinear dimension reduction in function approximation
- Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent
- SCNet: A Generalized Attention-based Model for Crack Fault Segmentation
- Training Efficiency and Robustness in Deep Learning
- 3D-Aware Semantic-Guided Generative Model for Human Synthesis
- Deep residential representations: Using unsupervised learning to unlock elevation data for geo-demographic prediction
- Joint Characterization of the Cryospheric Spectral Feature Space
- Active Learning for Domain Adaptation: An Energy-Based Approach
- FedRAD: Federated Robust Adaptive Distillation
- LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training
- Iterative Contrast-Classify For Semi-supervised Temporal Action Segmentation
- Newton methods based convolution neural networks using parallel processing
- TISE: Bag of Metrics for Text-to-Image Synthesis Evaluation
- InsCLR: Improving Instance Retrieval with Self-Supervision
All 222
- Residual Pathway Priors for Soft Equivariance Constraints
- Generalizing Off-Policy Learning under Sample Selection Bias
- ScaleVLAD: Improving Multimodal Sentiment Analysis via Multi-Scale Fusion of Locally Descriptors
- Breaking the Convergence Barrier: Optimization via Fixed-Time Convergent Flows
- Probabilistic Approach for Road-Users Detection
- Mixing Deep Learning and Multiple Criteria Optimization: An Application to Distributed Learning with Multiple Datasets
- MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment
- 3rd Place Solution for NeurIPS 2021 Shifts Challenge: Vehicle Motion Prediction
- How not to Lie with a Benchmark: Rearranging NLP Leaderboards
- Semantic-Sparse Colorization Network for Deep Exemplar-based Colorization
- Stationary Diffusion State Neural Estimation for Multiview Clustering
- Towards Generating Citation Sentences for Multiple References with Intent Control
- CSAW-M: An Ordinal Classification Dataset for Benchmarking Mammographic Masking of Cancer
- Putting 3D Spatially Sparse Networks on a Diet
- SIDNet: Learning Shading-aware Illumination Descriptor for Image Harmonization
- Optimal regularizations for data generation with probabilistic graphical models
- ViF-SD2E: A Robust Weakly-Supervised Method for Neural Decoding
- Borrowing from Similar Code: A Deep Learning NLP-Based Approach for Log Statement Automation
- Hierarchical Learning to Solve Partial Differential Equations Using Physics-Informed Neural Networks
- Youla-REN: Learning Nonlinear Feedback Policies with Robust Stability Guarantees
- Adaptive Group Collaborative Artificial Bee Colony Algorithm
- Resonating Minds -- Emergent Collaboration Through Hierarchical Active Inference
- Local Citation Recommendation with Hierarchical-Attention Text Encoder and SciBERT-based Reranking
- Sample Prior Guided Robust Model Learning to Suppress Noisy Labels
- Maximum Entropy Model-based Reinforcement Learning
- Video-Text Pre-training with Learned Regions
- Computing Class Hierarchies from Classifiers
- AST-Transformer: Encoding Abstract Syntax Trees Efficiently for Code Summarization
- MutualFormer: Multi-Modality Representation Learning via Cross-Diffusion Attention
- Overcoming the Domain Gap in Neural Action Representations
- Forex Trading Volatility Prediction using Neural Network Models
- Robust Robotic Control from Pixels using Contrastive Recurrent State-Space Models
- Video Frame Interpolation without Temporal Priors
- Learning Robust Recommender from Noisy Implicit Feedback
- A Unified Framework for Adversarial Attack and Defense in Constrained Feature Space
- Batch Normalization Tells You Which Filter is Important
- FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis
- CO2Sum:Contrastive Learning for Factual-Consistent Abstractive Summarization
- Risk-Aware Algorithms for Combinatorial Semi-Bandits
- Deep Learning-Based Carotid Artery Vessel Wall Segmentation in Black-Blood MRI Using Anatomical Priors
- Open-set 3D Object Detection
- FNR: A Similarity and Transformer-Based Approach to Detect Multi-Modal Fake News in Social Media
- "Just Drive": Colour Bias Mitigation for Semantic Segmentation in the Context of Urban Driving
- Near-Optimal Lower Bounds For Convex Optimization For All Orders of Smoothness
- Contrastive Adaptive Propagation Graph Neural Networks for Efficient Graph Learning
- Attention based Occlusion Removal for Hybrid Telepresence Systems
- Constrained Machine Learning: The Bagel Framework
- PTCT: Patches with 3D-Temporal Convolutional Transformer Network for Precipitation Nowcasting
- Who will dropout from university? Academic risk prediction based on interpretable machine learning
- Memory-efficient array redistribution through portable collective communication
- Controllable Video Captioning with an Exemplar Sentence
- The Second Place Solution for ICCV2021 VIPriors Instance Segmentation Challenge
- Extract Free Dense Labels from CLIP
- AutoGEL: An Automated Graph Neural Network with Explicit Link Information
- Automatic deforestation detectors based on frequentist statistics and their extensions for other spatial objects
- Syntax Customized Video Captioning by Imitating Exemplar Sentences
- Data-Driven Interaction Analysis of Line Failure Cascading in Power Grid Networks
- Stronger Baseline for Person Re-Identification
- Emotions are Subtle: Learning Sentiment Based Text Representations Using Contrastive Learning
- CloudWalker: Random walks for 3D point cloud shape analysis
- Bayesian Optimization over Permutation Spaces
- From Consensus to Disagreement: Multi-Teacher Distillation for Semi-Supervised Relation Extraction
- DKPLM: Decomposable Knowledge-enhanced Pre-trained Language Model for Natural Language Understanding
- ShuttleNet: Position-aware Fusion of Rally Progress and Player Styles for Stroke Forecasting in Badminton
- N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras
- Perform Like an Engine: A Closed-Loop Neural-Symbolic Learning Framework for Knowledge Graph Inference
- How global observation works in Federated Learning: Integrating vertical training into Horizontal Federated Learning
- Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips
- Inferring Prototypes for Multi-Label Few-Shot Image Classification with Word Vector Guided Attention
- GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation
- Graph4Rec: A Universal Toolkit with Graph Neural Networks for Recommender Systems
- Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data
- TBN-ViT: Temporal Bilateral Network with Vision Transformer for Video Scene Parsing
- TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework using Self-Supervised Multi-Task Learning
- Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation
- Learning Optimal Predictive Checklists
- Unconstrained Face Sketch Synthesis via Perception-Adaptive Network and A New Benchmark
- On Two XAI Cultures: A Case Study of Non-technical Explanations in Deployed AI System
- Improving Controllability of Educational Question Generation by Keyword Provision
- Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networks
- Differentiable Spatial Planning using Transformers
- Editing a classifier by rewriting its prediction rules
- SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency
- SwinTrack: A Simple and Strong Baseline for Transformer Tracking
- Embedding Decomposition for Artifacts Removal in EEG Signals
- Deep Transfer Learning: A Novel Collaborative Learning Model for Cyberattack Detection Systems in IoT Networks
- On Large Batch Training and Sharp Minima: A Fokker-Planck Perspective
- Evaluation of mathematical questioning strategies using data collected through weak supervision
- Trap of Feature Diversity in the Learning of MLPs
- Recommending with Recommendations
- Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification
- Consensus Graph Representation Learning for Better Grounded Image Captioning
- Adversarial Robustness of Deep Reinforcement Learning based Dynamic Recommender Systems
- Towards Personalization of User Preferences in Partially Observable Smart Home Environments
- Narrative Cartography with Knowledge Graphs
- Object-Centric Unsupervised Image Captioning
- Relational Graph Learning for Grounded Video Description Generation
- Vision Pair Learning: An Efficient Training Framework for Image Classification
- A Survey on Scenario-Based Testing for Automated Driving Systems in High-Fidelity Simulation
- Multi-Domain Transformer-Based Counterfactual Augmentation for Earnings Call Analysis
- Large-Scale Data Mining of Rapid Residue Detection Assay Data From HTML and PDF Documents: Improving Data Access and Visualization for Veterinarians
- Hierarchical Neural Implicit Pose Network for Animation and Motion Retargeting
- Personalized Federated Learning of Driver Prediction Models for Autonomous Driving
- Source Free Unsupervised Graph Domain Adaptation
- Temporally Resolution Decrement: Utilizing the Shape Consistency for Higher Computational Efficiency
- Maximum Consensus by Weighted Influences of Monotone Boolean Functions
- A Discrete-event-based Simulator for Distributed Deep Learning
- Visual-Semantic Transformer for Scene Text Recognition
- DPVI: A Dynamic-Weight Particle-Based Variational Inference Framework
- On Salience-Sensitive Sign Classification in Autonomous Vehicle Path Planning: Experimental Explorations with a Novel Dataset
- Generalized Closed-form Formulae for Feature-based Subpixel Alignment in Patch-based Matching
- Reward-Free Attacks in Multi-Agent Reinforcement Learning
- PartImageNet: A Large, High-Quality Dataset of Parts
- Context-Aware Online Client Selection for Hierarchical Federated Learning
- HyperSPNs: Compact and Expressive Probabilistic Circuits
- CDLNet: Noise-Adaptive Convolutional Dictionary Learning Network for Blind Denoising and Demosaicing
- ProtGNN: Towards Self-Explaining Graph Neural Networks
- Modeling human intention inference in continuous 3D domains by inverse planning and body kinematics
- Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL
- Context-Dependent Semantic Parsing for Temporal Relation Extraction
- Event Neural Networks
- Counterfactual Explanations via Latent Space Projection and Interpolation