{"list":"other","total":76,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"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":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"id":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"1805.12152","title":"Robustness May Be at Odds with Accuracy","created":"2018-05-30","cited_by_count":880},{"id":"1511.07528","title":"The Limitations of Deep Learning in Adversarial Settings","created":"2015-11-24","cited_by_count":790},{"id":"1902.06720","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","created":"2019-02-18","cited_by_count":738},{"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":"2007.08199","title":"Learning from Noisy Labels with Deep Neural Networks: A Survey","created":"2020-07-16","cited_by_count":582},{"id":"1901.08584","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","created":"2019-01-24","cited_by_count":566},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"id":"1801.00553","title":"Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey","created":"2018-01-02","cited_by_count":460},{"id":"1906.05271","title":"Does Learning Require Memorization? A Short Tale about a Long Tail","created":"2019-06-12","cited_by_count":460},{"id":"1605.07277","title":"Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples","created":"2016-05-24","cited_by_count":446},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"2007.00151","title":"Early-Learning Regularization Prevents Memorization of Noisy Labels","created":"2020-06-30","cited_by_count":416},{"id":"1901.06523","title":"Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks","created":"2019-01-19","cited_by_count":368},{"id":"2008.11687","title":"What is being transferred in transfer learning?","created":"2020-08-26","cited_by_count":368},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"2001.10528","title":"Identifying Mislabeled Data using the Area Under the Margin Ranking","created":"2020-01-28","cited_by_count":261},{"id":"2006.13554","title":"Normalized Loss Functions for Deep Learning with Noisy Labels","created":"2020-06-24","cited_by_count":257},{"id":"2110.12088","title":"Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations","created":"2021-10-22","cited_by_count":256},{"id":"1905.07121","title":"Simple Black-box Adversarial Attacks","created":"2019-05-17","cited_by_count":251},{"id":"1905.05040","title":"Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels","created":"2019-05-13","cited_by_count":209},{"id":"1905.12173","title":"On the Inductive Bias of Neural Tangent Kernels","created":"2019-05-29","cited_by_count":177},{"id":"1807.01251","title":"Training behavior of deep neural network in frequency domain","created":"2018-07-03","cited_by_count":174},{"id":"1812.00740","title":"Disentangling Adversarial Robustness and Generalization","created":"2018-12-03","cited_by_count":172},{"id":"1910.01842","title":"SELF: Learning to Filter Noisy Labels with Self-Ensembling","created":"2019-10-04","cited_by_count":164},{"id":"1812.05214","title":"Learning to Learn from Noisy Labeled Data","created":"2018-12-13","cited_by_count":160},{"id":"2002.09572","title":"The Break-Even Point on Optimization Trajectories of Deep Neural Networks","created":"2020-02-21","cited_by_count":150},{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145},{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141},{"id":"1810.11914","title":"Rademacher Complexity for Adversarially Robust Generalization","created":"2018-10-29","cited_by_count":132},{"id":"2011.04406","title":"A Survey of Label-noise Representation Learning: Past, Present and Future","created":"2020-11-09","cited_by_count":122},{"id":"2012.06421","title":"When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?","created":"2020-12-11","cited_by_count":104},{"id":"1902.01996","title":"Are All Layers Created Equal?","created":"2019-02-06","cited_by_count":94},{"id":"2106.15831","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","created":"2021-06-30","cited_by_count":75},{"id":"2006.10455","title":"What Do Neural Networks Learn When Trained With Random Labels?","created":"2020-06-18","cited_by_count":59},{"id":"2002.10657","title":"Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization","created":"2020-02-25","cited_by_count":41},{"id":"1912.00528","title":"The intriguing role of module criticality in the generalization of deep networks","created":"2019-12-02","cited_by_count":40},{"id":"2002.07933","title":"Improving Generalization by Controlling Label-Noise Information in Neural Network Weights","created":"2020-02-19","cited_by_count":35},{"id":"2101.11834","title":"Neural Architecture Search with Random Labels","created":"2021-01-28","cited_by_count":33},{"id":"2006.04492","title":"Speedy Performance Estimation for Neural Architecture Search","created":"2020-06-08","cited_by_count":24},{"id":"2205.01156","title":"SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labels","created":"2022-05-02","cited_by_count":24},{"id":"2012.04193","title":"Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels","created":"2020-12-08","cited_by_count":20},{"id":"2105.00303","title":"RATT: Leveraging Unlabeled Data to Guarantee Generalization","created":"2021-05-01","cited_by_count":20},{"id":"2010.14499","title":"A Bayesian Perspective on Training Speed and Model Selection","created":"2020-10-27","cited_by_count":19},{"id":"2012.12896","title":"How Does a Neural Network's Architecture Impact Its Robustness to Noisy Labels?","created":"2020-12-23","cited_by_count":12},{"id":"2004.13954","title":"Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNs","created":"2020-04-29","cited_by_count":11},{"id":"2002.06541","title":"Learning Not to Learn in the Presence of Noisy Labels","created":"2020-02-16","cited_by_count":9},{"id":"1911.09537","title":"Neural Network Memorization Dissection","created":"2019-11-21","cited_by_count":7},{"id":"2003.10647","title":"Robust and On-the-fly Dataset Denoising for Image Classification","created":"2020-03-24","cited_by_count":6},{"id":"2107.09957","title":"Memorization in Deep Neural Networks: Does the Loss Function matter?","created":"2021-07-21","cited_by_count":5},{"id":"2109.05000","title":"Assessing the Quality of the Datasets by Identifying Mislabeled Samples","created":"2021-09-10","cited_by_count":5}],"next_cursor":null}