{"total":218,"rows":[{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719,"area":null},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613,"area":null},{"id":"2103.01100","title":"Categorical Depth Distribution Network for Monocular 3D Object Detection","created":"2021-03-01","cited_by_count":327,"area":null},{"id":"2107.10834","title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","created":"2021-07-22","cited_by_count":128,"area":null},{"id":"2204.14211","title":"TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models","created":"2022-04-29","cited_by_count":119,"area":null},{"id":"2104.11896","title":"M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers","created":"2021-04-24","cited_by_count":74,"area":null},{"id":"2203.05662","title":"Point Density-Aware Voxels for LiDAR 3D Object Detection","created":"2022-03-10","cited_by_count":70,"area":null},{"id":"2204.11051","title":"$\\pi$BO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimization","created":"2022-04-23","cited_by_count":70,"area":null},{"id":"2110.03677","title":"Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect","created":"2021-10-07","cited_by_count":50,"area":null},{"id":"2205.01138","title":"Transformers in Time-series Analysis: A Tutorial","created":"2022-04-28","cited_by_count":46,"area":null},{"id":"2403.05618","title":"OmniJet-$\\alpha$: The first cross-task foundation model for particle physics","created":"2024-03-08","cited_by_count":43,"area":null},{"id":"2210.15031","title":"Characterizing Datapoints via Second-Split Forgetting","created":"2022-10-26","cited_by_count":37,"area":null},{"id":"2305.15694","title":"Learning Occupancy for Monocular 3D Object Detection","created":"2023-05-25","cited_by_count":36,"area":null},{"id":"2102.02320","title":"One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision","created":"2021-02-03","cited_by_count":33,"area":null},{"id":"2205.11775","title":"Constrained Monotonic Neural Networks","created":"2022-05-24","cited_by_count":32,"area":null},{"id":"2307.07944","title":"Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling","created":"2023-07-16","cited_by_count":28,"area":null},{"id":"2309.13549","title":"Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Dataset","created":"2023-09-24","cited_by_count":28,"area":null},{"id":"2210.09615","title":"Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection","created":"2022-10-18","cited_by_count":26,"area":null},{"id":"2110.10955","title":"Multi-label Classification with Partial Annotations using Class-aware Selective Loss","created":"2021-10-21","cited_by_count":25,"area":null},{"id":"2310.17087","title":"Good regularity creates large learning rate implicit biases: edge of stability, balancing, and catapult","created":"2023-10-26","cited_by_count":25,"area":null},{"id":"2103.14453","title":"Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifiers","created":"2021-03-26","cited_by_count":24,"area":null},{"id":"2105.05926","title":"Semantic Diversity Learning for Zero-Shot Multi-label Classification","created":"2021-05-12","cited_by_count":24,"area":null},{"id":"2203.08212","title":"AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning","created":"2022-03-15","cited_by_count":22,"area":null},{"id":"2311.14645","title":"A General Framework for User-Guided Bayesian Optimization","created":"2023-11-24","cited_by_count":22,"area":null},{"id":"2106.06195","title":"MlTr: Multi-label Classification with Transformer","created":"2021-06-11","cited_by_count":21,"area":null},{"id":"2212.07207","title":"MAELi: Masked Autoencoder for Large-Scale LiDAR Point Clouds","created":"2022-12-14","cited_by_count":20,"area":null},{"id":"2307.05390","title":"CrysMMNet: Multimodal Representation for Crystal Property Prediction","created":"2023-06-09","cited_by_count":18,"area":null},{"id":"2307.15196","title":"The Marginal Value of Momentum for Small Learning Rate SGD","created":"2023-07-27","cited_by_count":18,"area":null},{"id":"2405.17537","title":"CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale","created":"2024-05-27","cited_by_count":18,"area":null},{"id":"2203.00871","title":"Dense Voxel Fusion for 3D Object Detection","created":"2022-03-02","cited_by_count":17,"area":null},{"id":"2209.08473","title":"Bootstrap Generalization Ability from Loss Landscape Perspective","created":"2022-09-18","cited_by_count":16,"area":null},{"id":"2101.04117","title":"A Bayesian neural network predicts the dissolution of compact planetary systems","created":"2021-01-11","cited_by_count":15,"area":null},{"id":"2304.05403","title":"Isolated Sign Language Recognition based on Tree Structure Skeleton Images","created":"2023-04-10","cited_by_count":15,"area":null},{"id":"2105.10762","title":"AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly","created":"2021-05-22","cited_by_count":14,"area":null},{"id":"2109.13570","title":"Adaptive Informative Path Planning Using Deep Reinforcement Learning for UAV-based Active Sensing","created":"2021-09-28","cited_by_count":14,"area":null},{"id":"2308.01000","title":"MDT3D: Multi-Dataset Training for LiDAR 3D Object Detection Generalization","created":"2023-08-02","cited_by_count":14,"area":null},{"id":"2101.02672","title":"SA-Det3D: Self-Attention Based Context-Aware 3D Object Detection","created":"2021-01-07","cited_by_count":13,"area":null},{"id":"2103.06115","title":"Symmetry meets AI","created":"2021-03-10","cited_by_count":13,"area":null},{"id":"2104.10011","title":"Perceptual Loss for Robust Unsupervised Homography Estimation","created":"2021-04-20","cited_by_count":13,"area":null},{"id":"2303.15889","title":"Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition","created":"2023-03-28","cited_by_count":13,"area":null},{"id":"2201.09390","title":"AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networks","created":"2022-01-23","cited_by_count":12,"area":null},{"id":"2201.13063","title":"NeuralTailor: Reconstructing Sewing Pattern Structures from 3D Point Clouds of Garments","created":"2022-01-31","cited_by_count":10,"area":null},{"id":"2304.06937","title":"CAMM: Building Category-Agnostic and Animatable 3D Models from Monocular Videos","created":"2023-04-14","cited_by_count":10,"area":null},{"id":"2111.13309","title":"Data Augmented 3D Semantic Scene Completion with 2D Segmentation Priors","created":"2021-11-26","cited_by_count":9,"area":null},{"id":"2205.10049","title":"Assessing Demographic Bias Transfer from Dataset to Model: A Case Study in Facial Expression Recognition","created":"2022-05-20","cited_by_count":9,"area":null},{"id":"2210.00557","title":"Adaptive Smoothness-weighted Adversarial Training for Multiple Perturbations with Its Stability Analysis","created":"2022-10-02","cited_by_count":9,"area":null},{"id":"2305.06435","title":"Phase transitions in the mini-batch size for sparse and dense two-layer neural networks","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2506.13234","title":"The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions","created":"2025-06-16","cited_by_count":9,"area":null},{"id":"2511.01938","title":"The Geometry of Grokking: Norm Minimization on the Zero-Loss Manifold","created":"2025-11-02","cited_by_count":9,"area":null},{"id":"2107.04197","title":"REX: Revisiting Budgeted Training with an Improved Schedule","created":"2021-07-09","cited_by_count":8,"area":null},{"id":"2205.15575","title":"hmBERT: Historical Multilingual Language Models for Named Entity Recognition","created":"2022-05-31","cited_by_count":8,"area":null},{"id":"2210.05332","title":"Gender Stereotyping Impact in Facial Expression Recognition","created":"2022-10-11","cited_by_count":8,"area":null},{"id":"2308.05478","title":"Reviewing 3D Object Detectors in the Context of High-Resolution 3+1D Radar","created":"2023-08-10","cited_by_count":8,"area":null},{"id":"2411.19671","title":"On the Performance Analysis of Momentum Method: A Frequency Domain Perspective","created":"2024-11-29","cited_by_count":8,"area":null},{"id":"2502.01179","title":"Joint Localization and Activation Editing for Low-Resource Fine-Tuning","created":"2025-02-03","cited_by_count":8,"area":null},{"id":"2106.09178","title":"The Fishnet Open Images Database: A Dataset for Fish Detection and Fine-Grained Categorization in Fisheries","created":"2021-06-16","cited_by_count":7,"area":null},{"id":"2107.05202","title":"Delta Sampling R-BERT for limited data and low-light action recognition","created":"2021-07-12","cited_by_count":7,"area":null},{"id":"2304.04142","title":"Slideflow: Deep Learning for Digital Histopathology with Real-Time Whole-Slide Visualization","created":"2023-04-09","cited_by_count":7,"area":null},{"id":"2306.16016","title":"Positive Label Is All You Need for Multi-Label Classification","created":"2023-06-28","cited_by_count":7,"area":null},{"id":"2307.11608","title":"Learning minimal representations of stochastic processes with variational autoencoders","created":"2023-07-21","cited_by_count":7,"area":null},{"id":"2405.05241","title":"BenthicNet: A global compilation of seafloor images for deep learning applications","created":"2024-05-08","cited_by_count":7,"area":null},{"id":"2505.08685","title":"Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS) challenge results","created":"2025-05-13","cited_by_count":7,"area":null},{"id":"2106.08027","title":"Multivariate Business Process Representation Learning utilizing Gramian Angular Fields and Convolutional Neural Networks","created":"2021-06-15","cited_by_count":6,"area":null},{"id":"2108.06808","title":"Implicit Regularization of Bregman Proximal Point Algorithm and Mirror Descent on Separable Data","created":"2021-08-15","cited_by_count":6,"area":null},{"id":"2207.06080","title":"Efficient Augmentation for Imbalanced Deep Learning","created":"2022-07-13","cited_by_count":6,"area":null},{"id":"2208.08041","title":"InterTrack: Interaction Transformer for 3D Multi-Object Tracking","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2301.07407","title":"TAME: Attention Mechanism Based Feature Fusion for Generating Explanation Maps of Convolutional Neural Networks","created":"2023-01-18","cited_by_count":6,"area":null},{"id":"2410.14900","title":"DRACO: Differentiable Reconstruction for Arbitrary CBCT Orbits","created":"2024-10-18","cited_by_count":6,"area":null},{"id":"2506.00400","title":"Scaling Textual Gradients via Sampling-Based Momentum","created":"2025-05-31","cited_by_count":6,"area":null},{"id":"2506.11982","title":"Interpretable representation learning of quantum data enabled by probabilistic variational autoencoders","created":"2025-06-13","cited_by_count":6,"area":null},{"id":"2106.04462","title":"Muddling Label Regularization: Deep Learning for Tabular Datasets","created":"2021-06-08","cited_by_count":5,"area":null},{"id":"2109.09165","title":"Traffic-Net: 3D Traffic Monitoring Using a Single Camera","created":"2021-09-19","cited_by_count":5,"area":null},{"id":"2111.14157","title":"Implicit Equivariance in Convolutional Networks","created":"2021-11-28","cited_by_count":5,"area":null},{"id":"2212.05611","title":"Accelerating Self-Supervised Learning via Efficient Training Strategies","created":"2022-12-11","cited_by_count":5,"area":null},{"id":"2303.11419","title":"EPiC: Ensemble of Partial Point Clouds for Robust Classification","created":"2023-03-20","cited_by_count":5,"area":null},{"id":"2402.01514","title":"Mapping the Multiverse of Latent Representations","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2406.17405","title":"Less can be more: representational vs. stereotypical gender bias in facial expression recognition","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2509.13821","title":"Learning Minimal Representations of Many-Body Physics from Snapshots of a Quantum Simulator","created":"2025-09-17","cited_by_count":5,"area":null},{"id":"2102.12139","title":"Interpreting the Latent Space of Generative Adversarial Networks using Supervised Learning","created":"2021-02-24","cited_by_count":4,"area":null},{"id":"2105.04895","title":"Image Classification with Classic and Deep Learning Techniques","created":"2021-05-11","cited_by_count":4,"area":null},{"id":"2105.05758","title":"DEEMD: Drug Efficacy Estimation against SARS-CoV-2 based on cell Morphology with Deep multiple instance learning","created":"2021-05-10","cited_by_count":4,"area":null},{"id":"2111.10255","title":"An Analysis of the Influence of Transfer Learning When Measuring the Tortuosity of Blood Vessels","created":"2021-11-19","cited_by_count":4,"area":null},{"id":"2201.07199","title":"Invariant Representation Driven Neural Classifier for Anti-QCD Jet Tagging","created":"2022-01-18","cited_by_count":4,"area":null},{"id":"2202.07118","title":"Multi-task UNet: Jointly Boosting Saliency Prediction and Disease Classification on Chest X-ray Images","created":"2022-02-15","cited_by_count":4,"area":null},{"id":"2204.11548","title":"PedRecNet: Multi-task deep neural network for full 3D human pose and orientation estimation","created":"2022-04-25","cited_by_count":4,"area":null},{"id":"2204.13908","title":"Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time-Series Forecast","created":"2022-04-29","cited_by_count":4,"area":null},{"id":"2207.12218","title":"Cov3d: Detection of the presence and severity of COVID-19 from CT scans using 3D ResNets","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2209.06585","title":"Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image Classification","created":"2022-09-14","cited_by_count":4,"area":null},{"id":"2210.11078","title":"Large-batch Optimization for Dense Visual Predictions","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2304.07247","title":"The R-mAtrIx Net","created":"2023-04-14","cited_by_count":4,"area":null},{"id":"2307.14243","title":"Fluorescent Neuronal Cells v2: Multi-Task, Multi-Format Annotations for Deep Learning in Microscopy","created":"2023-07-26","cited_by_count":4,"area":null},{"id":"2309.14027","title":"TomOpt: Differential optimisation for task- and constraint-aware design of particle detectors in the context of muon tomography","created":"2023-09-25","cited_by_count":4,"area":null},{"id":"2310.07221","title":"Using Learnable Physics for Real-Time Exercise Form Recommendations","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2403.04523","title":"T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers","created":"2024-03-07","cited_by_count":4,"area":null},{"id":"2506.17826","title":"Actionable Interpretability via Causal Hypergraphs: Unravelling Batch Size Effects in Deep Learning","created":"2025-06-21","cited_by_count":4,"area":null},{"id":"2103.08105","title":"MBAPose: Mask and Bounding-Box Aware Pose Estimation of Surgical Instruments with Photorealistic Domain Randomization","created":"2021-03-15","cited_by_count":3,"area":null},{"id":"2103.11695","title":"Predicting brain-age from raw T 1 -weighted Magnetic Resonance Imaging data using 3D Convolutional Neural Networks","created":"2021-03-22","cited_by_count":3,"area":null},{"id":"2103.15345","title":"FixNorm: Dissecting Weight Decay for Training Deep Neural Networks","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2104.03054","title":"Artificial and beneficial -- Exploiting artificial images for aerial vehicle detection","created":"2021-04-07","cited_by_count":3,"area":null},{"id":"2110.08562","title":"BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements","created":"2021-10-16","cited_by_count":3,"area":null}],"next_cursor":"100"}