{"list":"other","total":56,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"1502.05767","title":"Automatic differentiation in machine learning: a survey","created":"2015-02-20","cited_by_count":855},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"2010.09670","title":"RobustBench: a standardized adversarial robustness benchmark","created":"2020-10-19","cited_by_count":661},{"id":"1807.09536","title":"End-to-End Incremental Learning","created":"2018-07-25","cited_by_count":597},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"1512.02595","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","created":"2015-12-08","cited_by_count":451},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"1804.09458","title":"Dynamic Few-Shot Visual Learning without Forgetting","created":"2018-04-25","cited_by_count":385},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"1402.4102","title":"Stochastic Gradient Hamiltonian Monte Carlo","created":"2014-02-17","cited_by_count":343},{"id":"2007.06823","title":"Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users","created":"2020-07-14","cited_by_count":338},{"id":"1401.0118","title":"Black Box Variational Inference","created":"2013-12-31","cited_by_count":319},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291},{"id":"2103.00123","title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training","created":"2021-02-27","cited_by_count":274},{"id":"2011.00050","title":"Dataset Meta-Learning from Kernel Ridge-Regression","created":"2020-10-30","cited_by_count":230},{"id":"2012.10630","title":"GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning","created":"2020-12-19","cited_by_count":226},{"id":"2205.14959","title":"Dataset Condensation via Efficient Synthetic-Data Parameterization","created":"2022-05-30","cited_by_count":188},{"id":"2206.00719","title":"Dataset Distillation using Neural Feature Regression","created":"2022-06-01","cited_by_count":177},{"id":"1603.00788","title":"Automatic Differentiation Variational Inference","created":"2016-03-02","cited_by_count":159},{"id":"2204.08499","title":"DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning","created":"2022-04-18","cited_by_count":147},{"id":"2211.11004","title":"Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation","created":"2022-11-20","cited_by_count":142},{"id":"2301.07014","title":"Dataset Distillation: A Comprehensive Review","created":"2023-01-17","cited_by_count":127},{"id":"2210.12067","title":"Efficient Dataset Distillation Using Random Feature Approximation","created":"2022-10-21","cited_by_count":111},{"id":"2202.02916","title":"Dataset Condensation with Contrastive Signals","created":"2022-02-07","cited_by_count":105},{"id":"2206.02916","title":"Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks","created":"2022-06-06","cited_by_count":104},{"id":"1807.04518","title":"Turning Big data into tiny data: Constant-size coresets for k-means, PCA and projective clustering","created":"2018-07-12","cited_by_count":94},{"id":"2302.14416","title":"DREAM: Efficient Dataset Distillation by Representative Matching","created":"2023-02-28","cited_by_count":94},{"id":"2006.08572","title":"Flexible Dataset Distillation: Learn Labels Instead of Images","created":"2020-06-15","cited_by_count":91},{"id":"1605.06423","title":"Coresets for Scalable Bayesian Logistic Regression","created":"2016-05-20","cited_by_count":79},{"id":"2204.07513","title":"Synthesizing Informative Training Samples with GAN","created":"2022-04-15","cited_by_count":77},{"id":"1802.01737","title":"Bayesian Coreset Construction via Greedy Iterative Geodesic Ascent","created":"2018-02-05","cited_by_count":68},{"id":"2207.09639","title":"DC-BENCH: Dataset Condensation Benchmark","created":"2022-07-20","cited_by_count":67},{"id":"2212.06152","title":"Accelerating Dataset Distillation via Model Augmentation","created":"2022-12-12","cited_by_count":62},{"id":"1710.05053","title":"Automated Scalable Bayesian Inference via Hilbert Coresets","created":"2017-10-13","cited_by_count":55},{"id":"1505.02827","title":"On Markov chain Monte Carlo methods for tall data","created":"2015-05-11","cited_by_count":50},{"id":"2001.05755","title":"ScaIL: Classifier Weights Scaling for Class Incremental Learning","created":"2020-01-16","cited_by_count":47},{"id":"2208.00311","title":"Delving into Effective Gradient Matching for Dataset Condensation","created":"2022-07-30","cited_by_count":40},{"id":"1906.03329","title":"Sparse Variational Inference: Bayesian Coresets from Scratch","created":"2019-06-07","cited_by_count":28},{"id":"2209.14609","title":"Dataset Distillation Using Parameter Pruning","created":"2022-09-29","cited_by_count":27},{"id":"1403.5693","title":"Firefly Monte Carlo: Exact MCMC with Subsets of Data","created":"2014-03-22","cited_by_count":23},{"id":"2203.05723","title":"Bayesian inference via sparse Hamiltonian flows","created":"2022-03-11","cited_by_count":12},{"id":"1706.02692","title":"The True Cost of Stochastic Gradient Langevin Dynamics","created":"2017-06-08","cited_by_count":11},{"id":"2210.06205","title":"On Divergence Measures for Bayesian Pseudocoresets","created":"2022-10-12","cited_by_count":10},{"id":"2203.09675","title":"Fast Bayesian Coresets via Subsampling and Quasi-Newton Refinement","created":"2022-03-18","cited_by_count":9},{"id":"1502.01510","title":"The Fundamental Incompatibility of Hamiltonian Monte Carlo and Data Subsampling","created":"2015-02-05","cited_by_count":7},{"id":"1609.03436","title":"Quasi-stationary Monte Carlo and the ScaLE Algorithm","created":"2016-09-12","cited_by_count":5}],"next_cursor":null}