mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 20 Jun 2022

166 papers

  1. Knowledge Distillation for Oriented Object Detection on Aerial ImagesKnowledge distillation → Detection and dense prediction distillation
  2. Real-time Full-stack Traffic Scene Perception for Autonomous Driving with Roadside CamerasEnd-to-end autonomous driving → VLMs for autonomous driving
  3. SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous VehiclesEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  4. DALL-E for Detection: Language-driven Compositional Image Synthesis for Object DetectionDiffusion models → Image generation, text-to-image and editing
  5. Deep Learning-Based Defect Classification and Detection in SEM Images
  6. Gait Cycle Reconstruction and Human Identification from Occluded Sequences
  7. CS2: A Controllable and Simultaneous Synthesizer of Images and Annotations with Minimal Human Intervention
  8. Cross-Modal Transformer GAN: A Brain Structure-Function Deep Fusing Framework for Alzheimer's Disease
  9. Remote Sensing Image Classification using Transfer Learning and Attention Based Deep Neural Network
  10. Deep reinforced active learning for multi-class image classification
  11. A Comprehensive Survey on Video Saliency Detection with Auditory Information: the Audio-visual Consistency Perceptual is the Key!
  12. Open Set Classification of Untranscribed Handwritten Documents
  13. Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review
  14. Business Document Information Extraction: Towards Practical Benchmarks
  15. A Novel Three-Dimensional Navigation Method for the Visually Impaired
  16. An Ontological Approach to Analysing Social Service Provisioning
  17. S2RL: Do We Really Need to Perceive All States in Deep Multi-Agent Reinforcement Learning?
  18. COVYT: Introducing the Coronavirus YouTube and TikTok speech dataset featuring the same speakers with and without infection
  19. Penalty Weights in QUBO Formulations: Permutation Problems
  20. On the Impossibility of Learning to Cooperate with Adaptive Partner Strategies in Repeated Games
  21. The Right Tool for the Job: Open-Source Auditing Tools in Machine Learning
  22. Metareview-informed Explainable Cytokine Storm Detection during CAR-T cell Therapy
  23. Neural Activation Patterns (NAPs): Visual Explainability of Learned Concepts
  24. Stop ordering machine learning algorithms by their explainability! A user-centered investigation of performance and explainability
  25. Autoencoder-based Attribute Noise Handling Method for Medical Data
  26. Generating Diverse Indoor Furniture Arrangements
  27. MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer
  28. Good Time to Ask: A Learning Framework for Asking for Help in Embodied Visual Navigation
  29. FedER: Federated Learning through Experience Replay and Privacy-Preserving Data Synthesis
  30. Identifiability of deep generative models without auxiliary information
  31. Classification Utility, Fairness, and Compactness via Tunable Information Bottleneck and R'enyi Measures
  32. MPA: MultiPath++ Based Architecture for Motion Prediction
  33. Understanding a Robot's Guiding Ethical Principles via Automatically Generated Explanations
  34. Deep Learning Models on CPUs: A Methodology for Efficient Training
  35. Test Time Transform Prediction for Open Set Histopathological Image Recognition
  36. Communication-Efficient Federated Learning With Data and Client Heterogeneity
  37. SynWMD: Syntax-aware Word Mover's Distance for Sentence Similarity Evaluation
  38. Intention-Aware Navigation in Crowds with Extended-Space POMDP Planning
  39. DNA: Proximal Policy Optimization with a Dual Network Architecture
  40. Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality
  41. flow-based clustering and spectral clustering: a comparison
  42. Deep Partial Least Squares for Empirical Asset Pricing
  43. Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments
  44. Limitations of the NTK for Understanding Generalization in Deep Learning
  45. When Does Re-initialization Work?
  46. Hyperparameter Importance of Quantum Neural Networks Across Small Datasets
  47. Model Optimization in Imbalanced Regression
  48. Measuring Class-Imbalance Sensitivity of Deterministic Performance Evaluation Metrics
  49. Mitigating Data Heterogeneity in Federated Learning with Data Augmentation
  50. Analysis of Thompson Sampling for Controlling Unknown Linear Diffusion Processes
  51. Noise Estimation in Gaussian Process Regression
  52. Critical Investigation of Failure Modes in Physics-informed Neural Networks
  53. Global Context Vision Transformers
  54. Seizure Detection and Prediction by Parallel Memristive Convolutional Neural Networks
  55. Short Video Uprising: How #BlackLivesMatter Content on TikTok Challenges the Protest Paradigm
  56. Quantum-machine-learning channel discrimination
  57. WOLONet: Wave Outlooker for Efficient and High Fidelity Speech Synthesis
  58. Inference-Based Quantum Sensing
  59. Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models
  60. A Langevin-like Sampler for Discrete Distributions
  61. Low-Precision Stochastic Gradient Langevin Dynamics
  62. Learning Optimal Flows for Non-Equilibrium Importance Sampling
  63. ORFD: A Dataset and Benchmark for Off-Road Freespace Detection
  64. Only Tails Matter: Average-Case Universality and Robustness in the Convex Regime
  65. Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders
  66. Multiple Fairness and Cardinality constraints for Students-Topics Grouping Problem
  67. Variational Quantum and Quantum-Inspired Clustering
  68. Latent Variable Modelling Using Variational Autoencoders: A survey
  69. Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world
  70. SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression
  71. KOLOMVERSE: Korea open large-scale image dataset for object detection in the maritime universe
  72. Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities
  73. Algorithmic Fairness and Vertical Equity: Income Fairness with IRS Tax Audit Models
  74. Regression of high dimensional angular momentum states of light
  75. A Neural Network Based Method with Transfer Learning for Genetic Data Analysis
  76. Understanding Robust Learning through the Lens of Representation Similarities
  77. WiFi-based Spatiotemporal Human Action Perception
  78. Towards Using Promises for Multi-Agent Cooperation in Goal Reasoning
  79. Additive Gaussian Processes Revisited
  80. Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias
  81. DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment
  82. M&M Mix: A Multimodal Multiview Transformer Ensemble
  83. Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification
  84. Practical Deepfake Detection: Vulnerabilities in Global Contexts
  85. Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation
  86. A Distributional Approach for Soft Clustering Comparison and Evaluation
  87. Exceedance Probability Forecasting via Regression for Significant Wave Height Prediction
  88. SSM-DTA: Breaking the Barriers of Data Scarcity in Drug-Target Affinity Prediction
  89. ConvGeN: Convex space learning improves deep-generative oversampling for tabular imbalanced classification on smaller datasets
  90. Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search
  91. Self-Supervised Consistent Quantization for Fully Unsupervised Image Retrieval
  92. Using Sum-Product Networks to Assess Uncertainty in Deep Active Learning
  93. The Makerere Radio Speech Corpus: A Luganda Radio Corpus for Automatic Speech Recognition
  94. Boosting Cross-Domain Speech Recognition with Self-Supervision
  95. Actively learning to learn causal relationships
  96. Test-time image-to-image translation ensembling improves out-of-distribution generalization in histopathology
  97. Quantitative CT texture-based method to predict diagnosis and prognosis of fibrosing interstitial lung disease patterns
  98. Bilingual by default: Voice Assistants and the role of code-switching in creating a bilingual user experience
  99. Towards Perspective-Based Specification of Machine Learning-Enabled Systems
  100. Time Gated Convolutional Neural Networks for Crop Classification
All 166
  1. Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold
  2. Visualizing and Understanding Contrastive Learning
  3. A Comparative Study on Application of Class-Imbalance Learning for Severity Prediction of Adverse Events Following Immunization
  4. Guided Safe Shooting: model based reinforcement learning with safety constraints
  5. Developing a Free and Open-source Automated Building Exterior Crack Inspection Software for Construction and Facility Managers
  6. Geo-NI: Geometry-aware Neural Interpolation for Light Field Rendering
  7. Semantic Labeling of High Resolution Images Using EfficientUNets and Transformers
  8. A Note on the Convergence of Mirrored Stein Variational Gradient Descent under (L0,L1)-Smoothness Condition
  9. Great Expectations: Unsupervised Inference of Suspense, Surprise and Salience in Storytelling
  10. The Role of Machine Learning in Cybersecurity
  11. FoR2M: Recognition and Repair of Foldings in Mesh Surfaces. Application to 3D Object Degradation
  12. Technical Report: Combining knowledge from Transfer Learning during training and Wide Resnets
  13. GiDR-DUN; Gradient Dimensionality Reduction -- Differences and Unification
  14. Distribution Regularized Self-Supervised Learning for Domain Adaptation of Semantic Segmentation
  15. Misspelling Semantics In Thai
  16. GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks
  17. Studying the role of named entities for content preservation in text style transfer
  18. EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL
  19. Benchmarking Constraint Inference in Inverse Reinforcement Learning
  20. MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation
  21. What Can be Seen is What You Get: Structure Aware Point Cloud Augmentation
  22. Performance Prediction in Major League Baseball by Long Short-Term Memory Networks
  23. A Machine Learning Data Fusion Model for Soil Moisture Retrieval
  24. Beyond IID: data-driven decision-making in heterogeneous environments
  25. A Symbolic Approach for Counterfactual Explanations
  26. Diversified Adversarial Attacks based on Conjugate Gradient Method
  27. Sampling Efficient Deep Reinforcement Learning through Preference-Guided Stochastic Exploration
  28. Analyzing B"uchi Automata with Graph Neural Networks
  29. Revisiting lp-constrained Softmax Loss: A Comprehensive Study
  30. SJ-HD^2R: Selective Joint High Dynamic Range and Denoising Imaging for Dynamic Scenes
  31. Interpretable machine learning optimization (InterOpt) for operational parameters: a case study of highly-efficient shale gas development
  32. Distortion-Aware Network Pruning and Feature Reuse for Real-time Video Segmentation
  33. Constrained Reinforcement Learning for Robotics via Scenario-Based Programming
  34. SPBERTQA: A Two-Stage Question Answering System Based on Sentence Transformers for Medical Texts
  35. Winning the CVPR'2022 AQTC Challenge: A Two-stage Function-centric Approach
  36. Efficient and Flexible Sublabel-Accurate Energy Minimization
  37. Domain-Adaptive Text Classification with Structured Knowledge from Unlabeled Data
  38. From Multi-agent to Multi-robot: A Scalable Training and Evaluation Platform for Multi-robot Reinforcement Learning
  39. 5th Place Solution for YouTube-VOS Challenge 2022: Video Object Segmentation
  40. Explicit and implicit models in infrared and visible image fusion
  41. FedSSO: A Federated Server-Side Second-Order Optimization Algorithm
  42. C-SENN: Contrastive Self-Explaining Neural Network
  43. Deep Random Vortex Method for Simulation and Inference of Navier-Stokes Equations
  44. Guardian Angel: A Novel Walking Aid for the Visually Impaired
  45. Shuffle Gaussian Mechanism for Differential Privacy
  46. Two-Dimensional Weisfeiler-Lehman Graph Neural Networks for Link Prediction
  47. A Novel Long-term Iterative Mining Scheme for Video Salient Object Detection
  48. Scalable Distributed Algorithms for Size-Constrained Submodular Maximization in the MapReduce and Adaptive Complexity Models
  49. LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
  50. An Empirical Analysis on the Vulnerabilities of End-to-End Speech Segregation Models
  51. Saliency Guided Inter- and Intra-Class Relation Constraints for Weakly Supervised Semantic Segmentation
  52. Capturing and Inferring Dense Full-Body Human-Scene Contact
  53. Dynamic Message Propagation Network for RGB-D Salient Object Detection
  54. Eliminating The Impossible, Whatever Remains Must Be True
  55. Variational Distillation for Multi-View Learning
  56. Policy Optimization with Linear Temporal Logic Constraints
  57. Meta-learning for Out-of-Distribution Detection via Density Estimation in Latent Space
  58. DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations
  59. Characterizing Human Actions in the Digital Platform by Temporal Context
  60. Hands-on Wireless Sensing with Wi-Fi: A Tutorial
  61. Temporal Link Prediction via Adjusted Sigmoid Function and 2-Simplex Sructure
  62. Simultaneous approximation of a smooth function and its derivatives by deep neural networks with piecewise-polynomial activations
  63. Robust One Round Federated Learning with Predictive Space Bayesian Inference
  64. Multiple Testing Framework for Out-of-Distribution Detection
  65. C^*-algebra Net: A New Approach Generalizing Neural Network Parameters to C^*-algebra
  66. The Fallacy of AI Functionality