{"list":"other","total":57,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"2106.11959","title":"Revisiting Deep Learning Models for Tabular Data","created":"2021-06-22","cited_by_count":740},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"2106.03253","title":"Tabular Data: Deep Learning is Not All You Need","created":"2021-06-06","cited_by_count":535},{"id":"1710.05381","title":"A systematic study of the class imbalance problem in convolutional neural networks","created":"2017-10-15","cited_by_count":513},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"2106.01342","title":"SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training","created":"2021-06-02","cited_by_count":319},{"id":"2103.10158","title":"TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation","created":"2021-03-18","cited_by_count":227},{"id":"2305.02997","title":"When Do Neural Nets Outperform Boosted Trees on Tabular Data?","created":"2023-05-04","cited_by_count":223},{"id":"2006.07529","title":"Rethinking the Value of Labels for Improving Class-Imbalanced Learning","created":"2020-06-13","cited_by_count":216},{"id":"2104.00466","title":"Improving Calibration for Long-Tailed Recognition","created":"2021-04-01","cited_by_count":212},{"id":"2203.05556","title":"On Embeddings for Numerical Features in Tabular Deep Learning","created":"2022-03-10","cited_by_count":186},{"id":"2004.00431","title":"M2m: Imbalanced Classification via Major-to-minor Translation","created":"2020-04-01","cited_by_count":134},{"id":"2110.05025","title":"Self-supervised Learning is More Robust to Dataset Imbalance","created":"2021-10-11","cited_by_count":123},{"id":"2206.04041","title":"Neural Collapse: A Review on Modelling Principles and Generalization","created":"2022-06-08","cited_by_count":95},{"id":"1806.00194","title":"Deep Imbalanced Learning for Face Recognition and Attribute Prediction","created":"2018-06-01","cited_by_count":91},{"id":"1401.0212","title":"Data-Driven Robust Optimization","created":"2013-12-31","cited_by_count":85},{"id":"2211.13609","title":"PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization","created":"2022-11-24","cited_by_count":76},{"id":"1704.07515","title":"Deep Over-sampling Framework for Classifying Imbalanced Data","created":"2017-04-25","cited_by_count":59},{"id":"2203.08124","title":"Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective","created":"2022-03-15","cited_by_count":57},{"id":"1906.03291","title":"Understanding Generalization through Visualizations","created":"2019-06-07","cited_by_count":54},{"id":"2004.00900","title":"Learning to Segment the Tail","created":"2020-04-02","cited_by_count":54},{"id":"1601.05150","title":"Factors in Finetuning Deep Model for object detection","created":"2016-01-20","cited_by_count":53},{"id":"2206.15306","title":"Transfer Learning with Deep Tabular Models","created":"2022-06-30","cited_by_count":52},{"id":"2210.06441","title":"How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization","created":"2022-10-12","cited_by_count":40},{"id":"2103.14005","title":"Contrasting Contrastive Self-Supervised Representation Learning Pipelines","created":"2021-03-25","cited_by_count":37},{"id":"2301.04644","title":"Does progress on ImageNet transfer to real-world datasets?","created":"2023-01-11","cited_by_count":35},{"id":"2010.05351","title":"Identifying Melanoma Images using EfficientNet Ensemble: Winning Solution to the SIIM-ISIC Melanoma Classification Challenge","created":"2020-10-11","cited_by_count":25},{"id":"1909.11155","title":"Anchor Loss: Modulating Loss Scale based on Prediction Difficulty","created":"2019-09-24","cited_by_count":14},{"id":"2106.09643","title":"MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data","created":"2021-06-17","cited_by_count":1}],"next_cursor":null}