mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 1 Apr 2021

204 papers

  1. Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical StudyKnowledge distillation → General knowledge distillation methods
  2. Neural Video Portrait Relighting in Real-time via Consistency ModelingDiffusion models → 3D, point cloud and scene generation
  3. Students are the Best Teacher: Exit-Ensemble Distillation with Multi-ExitsKnowledge distillation → General knowledge distillation methods
  4. Perspective, Survey and Trends: Public Driving Datasets and Toolsets for Autonomous Driving Virtual TestEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  5. Unsupervised Domain Expansion for Visual CategorizationKnowledge distillation → General knowledge distillation methods
  6. Embedded Self-Distillation in Compact Multi-Branch Ensemble Network for Remote Sensing Scene ClassificationKnowledge distillation → Detection and dense prediction distillation
  7. Reservoir Based Edge Training on RF Data To Deliver Intelligent and Efficient IoT Spectrum Sensors
  8. Replay in Deep Learning: Current Approaches and Missing Biological Elements
  9. An artificial intelligence and Internet of things based automated irrigation system
  10. Finding Experts in Social Media Data using a Hybrid Approach
  11. Unsupervised Speech Representation Learning for Behavior Modeling using Triplet Enhanced Contextualized Networks
  12. Collaborative Learning to Generate Audio-Video Jointly
  13. Prediction of Solar Radiation Using Artificial Neural Network
  14. Learning from Noisy Labels via Dynamic Loss Thresholding
  15. Neurological Status Classification Using Convolutional Neural Network
  16. Quick Line Outage Identification in Urban Distribution Grids via Smart Meters
  17. Qubit Routing using Graph Neural Network aided Monte Carlo Tree Search
  18. Novel DNNs for Stiff ODEs with Applications to Chemically Reacting Flows
  19. Combining conflicting ordinal quantum evidences utilizing individual reliability
  20. Deep Learning of Conjugate Mappings
  21. Visualizing computation in large-scale cellular automata
  22. CURIE: An Iterative Querying Approach for Reasoning About Situations
  23. Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation
  24. A Combined Deep Learning based End-to-End Video Coding Architecture for YUV Color Space
  25. Memorability: An image-computable measure of information utility
  26. Choice-Aware User Engagement Modeling andOptimization on Social Media
  27. FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds
  28. No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks
  29. Effect of Radiology Report Labeler Quality on Deep Learning Models for Chest X-Ray Interpretation
  30. Do RNN States Encode Abstract Phonological Processes?
  31. The Effects of Spectral Dimensionality Reduction on Hyperspectral Pixel Classification: A Case Study
  32. Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems
  33. "TL;DR:" Out-of-Context Adversarial Text Summarization and Hashtag Recommendation
  34. Collision-Aware Target-Driven Object Grasping in Constrained Environments
  35. MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluation
  36. Low-Resource Language Modelling of South African Languages
  37. Keyword Transformer: A Self-Attention Model for Keyword Spotting
  38. Canonical and Surface Morphological Segmentation for Nguni Languages
  39. Configurable Privacy-Preserving Automatic Speech Recognition
  40. Coalitional strategies for efficient individual prediction explanation
  41. SYSML: StYlometry with Structure and Multitask Learning: Implications for Darknet Forum Migrant Analysis
  42. Reconciling the Discrete-Continuous Divide: Towards a Mathematical Theory of Sparse Communication
  43. Reservoir-Based Distributed Machine Learning for Edge Operation
  44. Anytime Dense Prediction with Confidence Adaptivity
  45. Drug Discovery Approaches using Quantum Machine Learning
  46. Towards General Purpose Vision Systems
  47. Confidence Calibration for Domain Generalization under Covariate Shift
  48. Formal Methods for the Informal Engineer: Workshop Recommendations
  49. Graph Attention Networks for Channel Estimation in RIS-assisted Satellite IoT Communications
  50. Next Generation Multitarget Trackers: Random Finite Set Methods vs Transformer-based Deep Learning
  51. Out of a hundred trials, how many errors does your speaker verifier make?
  52. GABO: Graph Augmentations with Bi-level Optimization
  53. ProcessTransformer: Predictive Business Process Monitoring with Transformer Network
  54. BRepNet: A topological message passing system for solid models
  55. Multi-rate attention architecture for fast streamable Text-to-speech spectrum modeling
  56. Remote Sensing Image Classification with the SEN12MS Dataset
  57. NPMs: Neural Parametric Models for 3D Deformable Shapes
  58. Back to Square One: Superhuman Performance in Chutes and Ladders Through Deep Neural Networks and Tree Search
  59. SimPoE: Simulated Character Control for 3D Human Pose Estimation
  60. Multiview Pseudo-Labeling for Semi-supervised Learning from Video
  61. NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
  62. LoFTR: Detector-Free Local Feature Matching with Transformers
  63. A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification
  64. Group-Free 3D Object Detection via Transformers
  65. Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis
  66. In&Out : Diverse Image Outpainting via GAN Inversion
  67. PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting
  68. Cross-validation: what does it estimate and how well does it do it?
  69. TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness
  70. Unconstrained Scene Generation with Locally Conditioned Radiance Fields
  71. Deep Multi-Resolution Dictionary Learning for Histopathology Image Analysis
  72. Sampling and Filtering of Neural Machine Translation Distillation Data
  73. Recognizing and Splitting Conditional Sentences for Automation of Business Processes Management
  74. Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval
  75. Motion Guided Attention Fusion to Recognize Interactions from Videos
  76. Dynamic Silos: Increased Modularity in Intra-organizational Communication Networks during the Covid-19 Pandemic
  77. AmbiFC: Fact-Checking Ambiguous Claims with Evidence
  78. HLE-UPC at SemEval-2021 Task 5: Multi-Depth DistilBERT for Toxic Spans Detection
  79. Holdout-Based Fidelity and Privacy Assessment of Mixed-Type Synthetic Data
  80. RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering
  81. Residual Model Learning for Microrobot Control
  82. Regularized target encoding outperforms traditional methods in supervised machine learning with high cardinality features
  83. Fast DCTTS: Efficient Deep Convolutional Text-to-Speech
  84. RGB-D Local Implicit Function for Depth Completion of Transparent Objects
  85. Modular Adaptation for Cross-Domain Few-Shot Learning
  86. Composable Augmentation Encoding for Video Representation Learning
  87. Physics-informed neural networks for the shallow-water equations on the sphere
  88. The surprising impact of mask-head architecture on novel class segmentation
  89. Model Selection's Disparate Impact in Real-World Deep Learning Applications
  90. One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking
  91. NeRF-VAE: A Geometry Aware 3D Scene Generative Model
  92. Model Selection for Time Series Forecasting: Empirical Analysis of Different Estimators
  93. LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering
  94. Text to Image Generation with Semantic-Spatial Aware GAN
  95. Domain-Adversarial Training of Self-Attention Based Networks for Land Cover Classification using Multi-temporal Sentinel-2 Satellite Imagery
  96. A Front-End for Dense Monocular SLAM using a Learned Outlier Mask Prior
  97. Mining Wikidata for Name Resources for African Languages
  98. Deep Two-View Structure-from-Motion Revisited
  99. fairmodels: A Flexible Tool For Bias Detection, Visualization, And Mitigation
  100. NuPS: A Parameter Server for Machine Learning with Non-Uniform Parameter Access
All 204
  1. Machine Learning Applications to Kronian Magnetospheric Reconnection Classification
  2. A Joint Network for Grasp Detection Conditioned on Natural Language Commands
  3. PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN
  4. Bayesian Graph Convolutional Network for Traffic Prediction
  5. Linear Semantics in Generative Adversarial Networks
  6. Learning Foreground-Background Segmentation from Improved Layered GANs
  7. Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches
  8. Towards creativity characterization of generative models via group-based subset scanning
  9. Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors
  10. Improving Calibration for Long-Tailed Recognition
  11. Improved Image Generation via Sparse Modeling
  12. SCALoss: Side and Corner Aligned Loss for Bounding Box Regression
  13. Learning Rates for Multi-task Regularization Networks
  14. Semantic XAI for contextualized demand forecasting explanations
  15. Towards Evaluating and Training Verifiably Robust Neural Networks
  16. Touch-based Curiosity for Sparse-Reward Tasks
  17. Anchor Pruning for Object Detection
  18. Unsupervised Learning of Monocular Depth and Ego-Motion Using Multiple Masks
  19. Latent Space Data Assimilation by using Deep Learning
  20. Storchastic: A Framework for General Stochastic Automatic Differentiation
  21. WakaVT: A Sequential Variational Transformer for Waka Generation
  22. High-dimensional distributed semantic spaces for utterances
  23. Unsupervised Degradation Representation Learning for Blind Super-Resolution
  24. Learning with Neural Tangent Kernels in Near Input Sparsity Time
  25. Explaining COVID-19 and Thoracic Pathology Model Predictions by Identifying Informative Input Features
  26. quantum Case-Based Reasoning (qCBR)
  27. Avalanche: an End-to-End Library for Continual Learning
  28. Target Transformed Regression for Accurate Tracking
  29. Distributed support-vector-machine over dynamic balanced directed networks
  30. Commonsense Spatial Reasoning for Visually Intelligent Agents
  31. Optimization Algorithm for Feedback and Feedforward Policies towards Robot Control Robust to Sensing Failures
  32. Online Multiple Object Tracking with Cross-Task Synergy
  33. FeTaQA: Free-form Table Question Answering
  34. Low-Resource Neural Machine Translation for Southern African Languages
  35. Federated Few-Shot Learning with Adversarial Learning
  36. Evaluating Predictive Business Process Monitoring Approaches on Small Event Logs
  37. Efficient and Differentiable Shadow Computation for Inverse Problems
  38. Nine Potential Pitfalls when Designing Human-AI Co-Creative Systems
  39. Exploiting Relationship for Complex-scene Image Generation
  40. Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
  41. CycleDRUMS: Automatic Drum Arrangement For Bass Lines Using CycleGAN
  42. Decentralized and Model-Free Federated Learning: Consensus-Based Distillation in Function Space
  43. TrajeVAE: Controllable Human Motion Generation from Trajectories
  44. SpectralNET: Exploring Spatial-Spectral WaveletCNN for Hyperspectral Image Classification
  45. Reconstructing 3D Human Pose by Watching Humans in the Mirror
  46. Wide-Depth-Range 6D Object Pose Estimation in Space
  47. Mitigating Media Bias through Neutral Article Generation
  48. UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training
  49. On the Convergence Time of Federated Learning Over Wireless Networks Under Imperfect CSI
  50. Famous Companies Use More Letters in Logo:A Large-Scale Analysis of Text Area in Logo
  51. High-quality Low-dose CT Reconstruction Using Convolutional Neural Networks with Spatial and Channel Squeeze and Excitation
  52. STMTrack: Template-free Visual Tracking with Space-time Memory Networks
  53. Jigsaw Clustering for Unsupervised Visual Representation Learning
  54. Domain Invariant Adversarial Learning
  55. Semi-Supervised Domain Adaptation via Selective Pseudo Labeling and Progressive Self-Training
  56. Explore Image Deblurring via Blur Kernel Space
  57. Unsupervised Sound Localization via Iterative Contrastive Learning
  58. Normal vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extraction
  59. Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation
  60. Modeling High-order Interactions across Multi-interests for Micro-video Recommendation
  61. MeanShift++: Extremely Fast Mode-Seeking With Applications to Segmentation and Object Tracking
  62. EfficientNetV2: Smaller Models and Faster Training
  63. Arbitrary-Shaped Text Detection withAdaptive Text Region Representation
  64. Many-to-English Machine Translation Tools, Data, and Pretrained Models
  65. Learning to Track Instances without Video Annotations
  66. CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning
  67. A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions
  68. Mesh Graphormer
  69. Evaluating Neural Word Embeddings for Sanskrit
  70. The Compact Support Neural Network
  71. Detecting over/under-translation errors for determining adequacy in human translations
  72. Pinpointing the Memory Behaviors of DNN Training
  73. Using Python for Model Inference in Deep Learning
  74. Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processing
  75. LaPred: Lane-Aware Prediction of Multi-Modal Future Trajectories of Dynamic Agents
  76. Divergence Optimization for Noisy Universal Domain Adaptation
  77. High-Dimensional Differentially-Private EM Algorithm: Methods and Near-Optimal Statistical Guarantees
  78. Variational Inference MPC using Tsallis Divergence
  79. Self-supervised Motion Learning from Static Images
  80. Positive Sample Propagation along the Audio-Visual Event Line
  81. Optimizer Fusion: Efficient Training with Better Locality and Parallelism
  82. Multilingual and code-switching ASR challenges for low resource Indian languages
  83. A Survey on Natural Language Video Localization
  84. Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition
  85. Two-phase weakly supervised object detection with pseudo ground truth mining
  86. DF^2AM: Dual-level Feature Fusion and Affinity Modeling for RGB-Infrared Cross-modality Person Re-identification
  87. Fast Jacobian-Vector Product for Deep Networks
  88. Integrating Subgraph-aware Relation and DirectionReasoning for Question Answering
  89. Training Multi-bit Quantized and Binarized Networks with A Learnable Symmetric Quantizer
  90. Fusing RGBD Tracking and Segmentation Tree Sampling for Multi-Hypothesis Volumetric Segmentation
  91. AdaPool: A Diurnal-Adaptive Fleet Management Framework using Model-Free Deep Reinforcement Learning and Change Point Detection
  92. Unsupervised Person Re-identification via Simultaneous Clustering and Consistency Learning
  93. Graph-Based Intercategory and Intermodality Network for Multilabel Classification and Melanoma Diagnosis of Skin Lesions in Dermoscopy and Clinical Images
  94. Data-Driven Optimized Tracking Control Heuristic for MIMO Structures: A Balance System Case Study
  95. TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking
  96. An Energy-Efficient Quad-Camera Visual System for Autonomous Machines on FPGA Platform
  97. Trajectory Tracking of Underactuated Sea Vessels With Uncertain Dynamics: An Integral Reinforcement Learning Approach
  98. Sub-GMN: The Neural Subgraph Matching Network Model
  99. Less is More: Accelerating Faster Neural Networks Straight from JPEG
  100. Selective Feature Compression for Efficient Activity Recognition Inference
  101. Visual Attention in Imaginative Agents
  102. Self-harm: detection and support on Twitter
  103. Are Bias Mitigation Techniques for Deep Learning Effective?
  104. Improved and efficient inter-vehicle distance estimation using road gradients of both ego and target vehicles