{"list":"other","total":60,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"1904.05046","title":"Generalizing from a Few Examples: A Survey on Few-Shot Learning","created":"2019-04-10","cited_by_count":463},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"1612.04642","title":"Harmonic Networks: Deep Translation and Rotation Equivariance","created":"2016-12-14","cited_by_count":295},{"id":"1705.08741","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","created":"2017-05-24","cited_by_count":279},{"id":"1710.03667","title":"High-dimensional dynamics of generalization error in neural networks","created":"2017-10-10","cited_by_count":241},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"1802.08760","title":"Sensitivity and Generalization in Neural Networks: an Empirical Study","created":"2018-02-23","cited_by_count":189},{"id":"1907.04595","title":"Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks","created":"2019-07-10","cited_by_count":162},{"id":"2003.07064","title":"On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location","created":"2020-03-16","cited_by_count":142},{"id":"1706.05350","title":"L2 Regularization versus Batch and Weight Normalization","created":"2017-06-16","cited_by_count":124},{"id":"1810.12281","title":"Three Mechanisms of Weight Decay Regularization","created":"2018-10-29","cited_by_count":113},{"id":"2204.03632","title":"The Effects of Regularization and Data Augmentation are Class Dependent","created":"2022-04-07","cited_by_count":67},{"id":"1803.01814","title":"Norm matters: efficient and accurate normalization schemes in deep networks","created":"2018-03-05","cited_by_count":62},{"id":"1902.00423","title":"Do We Train on Test Data? Purging CIFAR of Near-Duplicates","created":"2019-02-01","cited_by_count":62},{"id":"2010.02916","title":"Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate","created":"2020-10-06","cited_by_count":59},{"id":"1905.13277","title":"Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence","created":"2019-05-30","cited_by_count":54},{"id":"2003.12843","title":"A Close Look at Deep Learning with Small Data","created":"2020-03-28","cited_by_count":54},{"id":"2007.02693","title":"Auxiliary Learning by Implicit Differentiation","created":"2020-06-22","cited_by_count":45},{"id":"2004.04328","title":"A Brief Prehistory of Double Descent","created":"2020-04-07","cited_by_count":44},{"id":"1901.09054","title":"Deep Learning on Small Datasets without Pre-Training using Cosine Loss","created":"2019-01-25","cited_by_count":41},{"id":"1712.01727","title":"OL\\'E: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep Learning","created":"2017-12-05","cited_by_count":37},{"id":"1703.08961","title":"Scaling the Scattering Transform: Deep Hybrid Networks","created":"2017-03-27","cited_by_count":35},{"id":"1809.06367","title":"Scattering Networks for Hybrid Representation Learning","created":"2018-09-17","cited_by_count":33},{"id":"2003.03977","title":"Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule","created":"2020-03-09","cited_by_count":25},{"id":"2112.03215","title":"Multi-scale Feature Learning Dynamics: Insights for Double Descent","created":"2021-12-06","cited_by_count":24},{"id":"2009.12583","title":"Small Data, Big Decisions: Model Selection in the Small-Data Regime","created":"2020-09-26","cited_by_count":23},{"id":"2209.03695","title":"Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes","created":"2022-09-08","cited_by_count":19},{"id":"1809.00981","title":"DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification","created":"2018-08-29","cited_by_count":18},{"id":"2107.09539","title":"Parametric Scattering Networks","created":"2021-07-20","cited_by_count":16},{"id":"1812.03965","title":"Guided Dropout","created":"2018-12-10","cited_by_count":14},{"id":"2207.12258","title":"Equivariance and Invariance Inductive Bias for Learning from Insufficient Data","created":"2022-07-25","cited_by_count":14},{"id":"2008.00261","title":"Distilling Visual Priors from Self-Supervised Learning","created":"2020-08-01","cited_by_count":13},{"id":"2108.13122","title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","created":"2021-08-30","cited_by_count":12},{"id":"2103.03768","title":"VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2021-03-05","cited_by_count":11},{"id":"1909.00114","title":"Towards Learning Affine-Invariant Representations via Data-Efficient CNNs","created":"2019-08-31","cited_by_count":10},{"id":"1803.11405","title":"Learning Structure and Strength of CNN Filters for Small Sample Size Training","created":"2018-03-30","cited_by_count":8},{"id":"2201.08625","title":"VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2022-01-21","cited_by_count":8},{"id":"1905.00135","title":"Harmonic Networks with Limited Training Samples","created":"2019-04-30","cited_by_count":7},{"id":"2304.11718","title":"No Free Lunch in Self Supervised Representation Learning","created":"2023-04-23","cited_by_count":7},{"id":"2202.11616","title":"ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing","created":"2022-02-23","cited_by_count":4},{"id":"2212.12478","title":"Image Classification with Small Datasets: Overview and Benchmark","created":"2022-12-23","cited_by_count":4},{"id":"2305.19688","title":"VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2023-05-31","cited_by_count":4},{"id":"2109.13561","title":"A Strong Baseline for the VIPriors Data-Efficient Image Classification Challenge","created":"2021-09-28","cited_by_count":2}],"next_cursor":null}