{"list":"other","total":68,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"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":"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":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"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":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"2103.00065","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","created":"2021-02-26","cited_by_count":427},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1904.11238","title":"Unsupervised Label Noise Modeling and Loss Correction","created":"2019-04-25","cited_by_count":328},{"id":"1704.04289","title":"Stochastic Gradient Descent as Approximate Bayesian Inference","created":"2017-04-13","cited_by_count":300},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293},{"id":"1912.07145","title":"PyHessian: Neural Networks Through the Lens of the Hessian","created":"2019-12-16","cited_by_count":292},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"1802.06509","title":"On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization","created":"2018-02-19","cited_by_count":284},{"id":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"1708.02709","title":"Recent Trends in Deep Learning Based Natural Language Processing","created":"2017-08-09","cited_by_count":263},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260},{"id":"1705.08292","title":"The Marginal Value of Adaptive Gradient Methods in Machine Learning","created":"2017-05-23","cited_by_count":250},{"id":"2003.02218","title":"The large learning rate phase of deep learning: the catapult mechanism","created":"2020-03-04","cited_by_count":216},{"id":"1902.09843","title":"Adaptive Gradient Methods with Dynamic Bound of Learning Rate","created":"2019-02-26","cited_by_count":183},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172},{"id":"1610.02915","title":"Deep Pyramidal Residual Networks","created":"2016-10-10","cited_by_count":163},{"id":"2104.07876","title":"Deep Stable Learning for Out-Of-Distribution Generalization","created":"2021-04-16","cited_by_count":153},{"id":"2002.09572","title":"The Break-Even Point on Optimization Trajectories of Deep Neural Networks","created":"2020-02-21","cited_by_count":150},{"id":"2009.11162","title":"Implicit Gradient Regularization","created":"2020-09-23","cited_by_count":146},{"id":"2110.03141","title":"Efficient Sharpness-aware Minimization for Improved Training of Neural Networks","created":"2021-10-07","cited_by_count":137},{"id":"1710.06451","title":"A Bayesian Perspective on Generalization and Stochastic Gradient Descent","created":"2017-10-17","cited_by_count":135},{"id":"2203.02714","title":"Towards Efficient and Scalable Sharpness-Aware Minimization","created":"2022-03-05","cited_by_count":129},{"id":"2202.03599","title":"Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning","created":"2022-02-08","cited_by_count":122},{"id":"1907.04164","title":"Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model","created":"2019-07-09","cited_by_count":117},{"id":"2001.02394","title":"Convolutional Networks with Dense Connectivity","created":"2020-01-08","cited_by_count":98},{"id":"2205.14083","title":"Sharpness-Aware Training for Free","created":"2022-05-27","cited_by_count":95},{"id":"1806.06763","title":"Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks","created":"2018-06-18","cited_by_count":90},{"id":"1902.00744","title":"Asymmetric Valleys: Beyond Sharp and Flat Local Minima","created":"2019-02-02","cited_by_count":90},{"id":"2001.00939","title":"Relative Flatness and Generalization","created":"2020-01-03","cited_by_count":88},{"id":"1802.08241","title":"Hessian-based Analysis of Large Batch Training and Robustness to Adversaries","created":"2018-02-22","cited_by_count":87},{"id":"2210.05177","title":"Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach","created":"2022-10-11","cited_by_count":70},{"id":"2206.10654","title":"On the Maximum Hessian Eigenvalue and Generalization","created":"2022-06-21","cited_by_count":57},{"id":"2210.05497","title":"Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models","created":"2022-10-11","cited_by_count":42},{"id":"2006.15815","title":"Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum","created":"2020-06-29","cited_by_count":40},{"id":"2107.06219","title":"Towards Unsupervised Domain Generalization","created":"2021-07-13","cited_by_count":40},{"id":"1711.06673","title":"Neon2: Finding Local Minima via First-Order Oracles","created":"2017-11-17","cited_by_count":36},{"id":"1711.01944","title":"First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time","created":"2017-11-03","cited_by_count":29},{"id":"1911.08192","title":"Information-Theoretic Local Minima Characterization and Regularization","created":"2019-11-19","cited_by_count":14},{"id":"1902.08234","title":"An Empirical Study of Large-Batch Stochastic Gradient Descent with Structured Covariance Noise","created":"2019-02-21","cited_by_count":13}],"next_cursor":null}