{"list":"other","total":71,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"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":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"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":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"1711.09601","title":"Memory Aware Synapses: Learning what (not) to forget","created":"2017-11-27","cited_by_count":1105},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"1711.05769","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","created":"2017-11-15","cited_by_count":898},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1801.10112","title":"Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence","created":"2018-01-30","cited_by_count":742},{"id":"1905.13260","title":"Large Scale Incremental Learning","created":"2019-05-30","cited_by_count":732},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"1801.01423","title":"Overcoming catastrophic forgetting with hard attention to the task","created":"2018-01-04","cited_by_count":681},{"id":"1807.09536","title":"End-to-End Incremental Learning","created":"2018-07-25","cited_by_count":597},{"id":"1903.08671","title":"Gradient based sample selection for online continual learning","created":"2019-03-20","cited_by_count":571},{"id":"1908.04742","title":"Online Continual Learning with Maximally Interfered Retrieval","created":"2019-08-11","cited_by_count":379},{"id":"1611.06194","title":"Expert Gate: Lifelong Learning with a Network of Experts","created":"2016-11-18","cited_by_count":372},{"id":"1708.02072","title":"Measuring Catastrophic Forgetting in Neural Networks","created":"2017-08-07","cited_by_count":360},{"id":"1905.11001","title":"On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks","created":"2019-05-27","cited_by_count":305},{"id":"1705.03550","title":"CORe50: a New Dataset and Benchmark for Continuous Object Recognition","created":"2017-05-09","cited_by_count":289},{"id":"1912.02315","title":"12-in-1: Multi-Task Vision and Language Representation Learning","created":"2019-12-05","cited_by_count":278},{"id":"1808.01204","title":"Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data","created":"2018-08-03","cited_by_count":261},{"id":"1811.08051","title":"Learning without Memorizing","created":"2018-11-20","cited_by_count":250},{"id":"1905.13210","title":"Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks","created":"2019-05-30","cited_by_count":222},{"id":"1805.07810","title":"Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting","created":"2018-05-20","cited_by_count":201},{"id":"1910.02509","title":"REMIND Your Neural Network to Prevent Catastrophic Forgetting","created":"2019-10-06","cited_by_count":197},{"id":"1904.03137","title":"Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning","created":"2019-04-05","cited_by_count":182},{"id":"1711.10563","title":"FearNet: Brain-Inspired Model for Incremental Learning","created":"2017-11-28","cited_by_count":177},{"id":"1902.04674","title":"Towards moderate overparameterization: global convergence guarantees for training shallow neural networks","created":"2019-02-12","cited_by_count":176},{"id":"1803.10082","title":"Efficient parametrization of multi-domain deep neural networks","created":"2018-03-27","cited_by_count":168},{"id":"1809.05922","title":"Memory Efficient Experience Replay for Streaming Learning","created":"2018-09-16","cited_by_count":128},{"id":"1903.12648","title":"Overcoming Catastrophic Forgetting with Unlabeled Data in the Wild","created":"2019-03-29","cited_by_count":111},{"id":"1705.04228","title":"Incremental Learning Through Deep Adaptation","created":"2017-05-11","cited_by_count":108},{"id":"2011.01844","title":"A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks","created":"2020-11-03","cited_by_count":107},{"id":"1704.01920","title":"Encoder Based Lifelong Learning","created":"2017-04-06","cited_by_count":102},{"id":"1607.00122","title":"Less-forgetting Learning in Deep Neural Networks","created":"2016-07-01","cited_by_count":97},{"id":"1801.02929","title":"Data Augmentation by Pairing Samples for Images Classification","created":"2018-01-09","cited_by_count":96},{"id":"1911.06987","title":"Faster AutoAugment: Learning Augmentation Strategies using Backpropagation","created":"2019-11-16","cited_by_count":96},{"id":"1909.01520","title":"Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis","created":"2019-09-04","cited_by_count":92},{"id":"2104.04132","title":"Replay in Deep Learning: Current Approaches and Missing Biological Elements","created":"2021-04-01","cited_by_count":72},{"id":"2003.05034","title":"SuperMix: Supervising the Mixing Data Augmentation","created":"2020-03-10","cited_by_count":58},{"id":"2103.14010","title":"Self-Supervised Training Enhances Online Continual Learning","created":"2021-03-25","cited_by_count":54},{"id":"2203.10681","title":"Online Continual Learning for Embedded Devices","created":"2022-03-21","cited_by_count":49},{"id":"2001.05755","title":"ScaIL: Classifier Weights Scaling for Class Incremental Learning","created":"2020-01-16","cited_by_count":47},{"id":"1907.07844","title":"Growing a Brain: Fine-Tuning by Increasing Model Capacity","created":"2019-07-18","cited_by_count":43},{"id":"2008.06439","title":"RODEO: Replay for Online Object Detection","created":"2020-08-14","cited_by_count":35},{"id":"1802.05800","title":"Tree-CNN: A Hierarchical Deep Convolutional Neural Network for Incremental Learning","created":"2018-02-15","cited_by_count":34},{"id":"1612.03770","title":"Neurogenesis Deep Learning","created":"2016-12-12","cited_by_count":32},{"id":"1703.06683","title":"A Systematic Study of Online Class Imbalance Learning with Concept Drift","created":"2017-03-20","cited_by_count":28},{"id":"2007.16008","title":"Multi-task learning for natural language processing in the 2020s: where are we going?","created":"2020-07-22","cited_by_count":27},{"id":"1812.00500","title":"Multi-task Learning of Hierarchical Vision-Language Representation","created":"2018-12-03","cited_by_count":26},{"id":"1908.08017","title":"Knowledge transfer in deep block-modular neural networks","created":"2019-07-24","cited_by_count":14},{"id":"1705.00744","title":"A Strategy for an Uncompromising Incremental Learner","created":"2017-05-02","cited_by_count":9},{"id":"1606.02355","title":"Active Long Term Memory Networks","created":"2016-06-07","cited_by_count":4},{"id":"2104.03309","title":"Streaming Self-Training via Domain-Agnostic Unlabeled Images","created":"2021-04-07","cited_by_count":3},{"id":"2107.13054","title":"Exceeding the Limits of Visual-Linguistic Multi-Task Learning","created":"2021-07-27","cited_by_count":3}],"next_cursor":null}