Papers
Thu 9 Dec 2021
168 papers
- Error-Aware Imitation Learning from Teleoperation Data for Mobile ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
- Spinning Language Models: Risks of Propaganda-As-A-Service and CountermeasuresLLM safety and security → Backdoor and data poisoning attacks
- DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion ModelDiffusion models → Medical imaging and segmentation
- Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic ContractionDiffusion models → Inverse problems and image restoration
- Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic PriorEnd-to-end autonomous driving → Adversarial scenarios and safety testing
- Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature ImitationKnowledge distillation → Detection and dense prediction distillation
- DR3: Value-Based Deep Reinforcement Learning Requires Explicit RegularizationOffline RL and imitation learning from data → Offline RL algorithms
- Advancing Deep Residual Learning by Solving the Crux of Degradation in Spiking Neural Networks
- Relating Blindsight and AI: A Review
- Are E2E ASR models ready for an industrial usage?
- Obtaining Calibrated Probabilities with Personalized Ranking Models
- Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution
- Multi-objective simulation optimization of the adhesive bonding process of materials
- You Can Wash Hands Better: Accurate Daily Handwashing Assessment with a Smartwatch
- Online Adaptation of Neural Network Models by Modified Extended Kalman Filter for Customizable and Transferable Driving Behavior Prediction
- Extending AdamW by Leveraging Its Second Moment and Magnitude
- Specificity-Preserving Federated Learning for MR Image Reconstruction
- MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning
- On the Relation between Prediction and Imputation Accuracy under Missing Covariates
- An Experimental Design Perspective on Model-Based Reinforcement Learning
- On multivariate randomized classification trees: l0-based sparsity, VC~dimension and decomposition methods
- Transfer learning using deep neural networks for Ear Presentation Attack Detection: New Database for PAD
- KartalOl: Transfer learning using deep neural network for iris segmentation and localization: New dataset for iris segmentation
- The Fundamental Limits of Interval Arithmetic for Neural Networks
- Injecting Semantic Concepts into End-to-End Image Captioning
- MantissaCam: Learning Snapshot High-dynamic-range Imaging with Perceptually-based In-pixel Irradiance Encoding
- Hidden Path Selection Network for Semantic Segmentation of Remote Sensing Images
- CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directions
- Learning Generalizable Behavior via Visual Rewrite Rules
- Road Extraction from Overhead Images with Graph Neural Networks
- Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learning
- 7th AI Driving Olympics: 1st Place Report for Panoptic Tracking
- Compositional Generalization for Natural Language Interfaces to Web APIs
- Reinforcement Learning with Almost Sure Constraints
- Self-Supervised Bot Play for Conversational Recommendation with Justifications
- Context-aware Health Event Prediction via Transition Functions on Dynamic Disease Graphs
- Word Embeddings via Causal Inference: Gender Bias Reducing and Semantic Information Preserving
- Contextualized Spatio-Temporal Contrastive Learning with Self-Supervision
- Annotation-efficient cancer detection with report-guided lesion annotation for deep learning-based prostate cancer detection in bpMRI
- Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring
- Classification of Anuran Frog Species Using Machine Learning
- Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement
- Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing
- GAN-Supervised Dense Visual Alignment
- HairCLIP: Design Your Hair by Text and Reference Image
- Exploring the Equivalence of Siamese Self-Supervised Learning via A Unified Gradient Framework
- NeRF for Outdoor Scene Relighting
- CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields
- Searching Parameterized AP Loss for Object Detection
- PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning
- PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures
- A Shared Representation for Photorealistic Driving Simulators
- Spatio-temporal Relation Modeling for Few-shot Action Recognition
- Plenoxels: Radiance Fields without Neural Networks
- Multimodal Conditional Image Synthesis with Product-of-Experts GANs
- Fair Community Detection and Structure Learning in Heterogeneous Graphical Models
- IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo
- Rethinking the Authorship Verification Experimental Setups
- Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation
- Self-Supervised Keypoint Discovery in Behavioral Videos
- On Convergence of Federated Averaging Langevin Dynamics
- BLT: Bidirectional Layout Transformer for Controllable Layout Generation
- Continuation Path with Linear Convergence Rate
- Provable Continual Learning via Sketched Jacobian Approximations
- Extending the WILDS Benchmark for Unsupervised Adaptation
- A Survey on Echo Chambers on Social Media: Description, Detection and Mitigation
- Locally Shifted Attention With Early Global Integration
- Critical configurations for two projective views, a new approach
- A Novel Tropical Geometry-based Interpretable Machine Learning Method: Application in Prognosis of Advanced Heart Failure
- A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulation
- Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies
- Opinion Extraction as A Structured Sentiment Analysis using Transformers
- Illumination and Temperature-Aware Multispectral Networks for Edge-Computing-Enabled Pedestrian Detection
- End-to-End Learning of Joint Geometric and Probabilistic Constellation Shaping
- Gradient-matching coresets for continual learning
- Millimeter Wave Localization with Imperfect Training Data using Shallow Neural Networks
- Exploring Event-driven Dynamic Context for Accident Scene Segmentation
- Mutual Adversarial Training: Learning together is better than going alone
- Wikidated 1.0: An Evolving Knowledge Graph Dataset of Wikidata's Revision History
- The Peril of Popular Deep Learning Uncertainty Estimation Methods
- Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRF
- Sparse-View CT Reconstruction using Recurrent Stacked Back Projection
- Robust Weakly Supervised Learning for COVID-19 Recognition Using Multi-Center CT Images
- PE-former: Pose Estimation Transformer
- A fully-differentiable compressible high-order computational fluid dynamics solver
- Bringing Atomistic Deep Learning to Prime Time
- AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach
- How Universal is Genre in Universal Dependencies?
- CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation
- Model-Agnostic Hybrid Numerical Weather Prediction and Machine Learning Paradigm for Solar Forecasting in the Tropics
- Machine Learning for Utility Prediction in Argument-Based Computational Persuasion
- Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN Ensembles
- Automated Side Channel Analysis of Media Software with Manifold Learning
- A Simple but Effective Bidirectional Framework for Relational Triple Extraction
- A Training Framework for Stereo-Aware Speech Enhancement using Deep Neural Networks
- DVHN: A Deep Hashing Framework for Large-scale Vehicle Re-identification
- Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers
- Measuring Wind Turbine Health Using Drifting Concepts
- Self-Supervised Image-to-Text and Text-to-Image Synthesis
- A More Stable Accelerated Gradient Method Inspired by Continuous-Time Perspective
All 168
- Few-Shot Keypoint Detection as Task Adaptation via Latent Embeddings
- PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis
- Latent Space Explanation by Intervention
- Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer
- A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer
- Forecast Evaluation in Large Cross-Sections of Realized Volatility
- Semantic Search as Extractive Paraphrase Span Detection
- Evaluating saliency methods on artificial data with different background types
- Nice perfume. How long did you marinate in it? Multimodal Sarcasm Explanation
- KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddings
- 3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis
- A New Measure of Model Redundancy for Compressed Convolutional Neural Networks
- ScaleNet: A Shallow Architecture for Scale Estimation
- Siamese Attribute-missing Graph Auto-encoder
- Multimodal Fake News Detection
- Avoiding C-hacking when evaluating survival distribution predictions with discrimination measures
- Explainability of the Implications of Supervised and Unsupervised Face Image Quality Estimations Through Activation Map Variation Analyses in Face Recognition Models
- Multimodal Pre-Training Model for Sequence-based Prediction of Protein-Protein Interaction
- Next Steps: Learning a Disentangled Gait Representation for Versatile Quadruped Locomotion
- Effective dimension of machine learning models
- Combining Textual Features for the Detection of Hateful and Offensive Language
- GPU backed Data Mining on Android Devices
- Complexity assessments for decidable fragments of Set Theory. IV: A quadratic reduction of constraints over nested sets to Boolean formulae
- Detecting potentially harmful and protective suicide-related content on twitter: A machine learning approach
- VMAgent: Scheduling Simulator for Reinforcement Learning
- Regularized Modal Regression on Markov-dependent Observations: A Theoretical Assessment
- Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection
- Adaptive Methods for Aggregated Domain Generalization
- 3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection
- HBReID: Harder Batch for Re-identification
- Does Redundancy in AI Perception Systems Help to Test for Super-Human Automated Driving Performance?
- High-Dimensional Stock Portfolio Trading with Deep Reinforcement Learning
- Modelling Lips-State Detection Using CNN for Non-Verbal Communications
- Co-evolutionary hybrid intelligence
- LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading
- Superpixel-Based Building Damage Detection from Post-earthquake Imagery Using Deep Neural Networks
- Learning multiple gaits of quadruped robot using hierarchical reinforcement learning
- Asynchronous Semi-Decentralized Federated Edge Learning for Heterogeneous Clients
- From Good to Best: Two-Stage Training for Cross-lingual Machine Reading Comprehension
- New Tight Relaxations of Rank Minimization for Multi-Task Learning
- Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning
- Reducing Catastrophic Forgetting in Self Organizing Maps with Internally-Induced Generative Replay
- One-dimensional Deep Low-rank and Sparse Network for Accelerated MRI
- Amicable Aid: Perturbing Images to Improve Classification Performance
- Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Vision
- Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search
- Implicit Feature Refinement for Instance Segmentation
- Ymir: A Supervised Ensemble Framework for Multivariate Time Series Anomaly Detection
- Fast Point Transformer
- Unsupervised Complementary-aware Multi-process Fusion for Visual Place Recognition
- Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges
- CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNet
- Trajectory-Constrained Deep Latent Visual Attention for Improved Local Planning in Presence of Heterogeneous Terrain
- Clairvoyance: Intelligent Route Planning for Electric Buses Based on Urban Big Data
- SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations
- A Note on Comparison of F-measures
- DualFormer: Local-Global Stratified Transformer for Efficient Video Recognition
- Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation
- Dual Cluster Contrastive learning for Object Re-Identification
- A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inverse
- Extending nn-UNet for brain tumor segmentation
- BACON: Band-limited Coordinate Networks for Multiscale Scene Representation
- Autoregressive Quantile Flows for Predictive Uncertainty Estimation
- Differentially Private Ensemble Classifiers for Data Streams
- Recurrent Glimpse-based Decoder for Detection with Transformer
- Towards Neural Functional Program Evaluation
- Transferability Properties of Graph Neural Networks
- Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection