{"list":"other","total":77,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"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":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1806.00582","title":"Federated Learning with Non-IID Data","created":"2018-06-02","cited_by_count":1108},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"1909.06335","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","created":"2019-09-13","cited_by_count":851},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"1812.01097","title":"LEAF: A Benchmark for Federated Settings","created":"2018-12-03","cited_by_count":792},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2103.16257","title":"Model-Contrastive Federated Learning","created":"2021-03-30","cited_by_count":766},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"2002.06440","title":"Federated Learning with Matched Averaging","created":"2020-02-15","cited_by_count":564},{"id":"2111.04263","title":"Federated Learning Based on Dynamic Regularization","created":"2021-11-08","cited_by_count":562},{"id":"1905.12022","title":"Bayesian Nonparametric Federated Learning of Neural Networks","created":"2019-05-28","cited_by_count":387},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"1901.09960","title":"Using Pre-Training Can Improve Model Robustness and Uncertainty","created":"2019-01-28","cited_by_count":373},{"id":"2008.11687","title":"What is being transferred in transfer learning?","created":"2020-08-26","cited_by_count":368},{"id":"2004.06100","title":"Pretrained Transformers Improve Out-of-Distribution Robustness","created":"2020-04-13","cited_by_count":294},{"id":"2006.07529","title":"Rethinking the Value of Labels for Improving Class-Imbalanced Learning","created":"2020-06-13","cited_by_count":216},{"id":"2011.13377","title":"How Well Do Self-Supervised Models Transfer?","created":"2020-11-26","cited_by_count":213},{"id":"2103.01988","title":"Self-supervised Pretraining of Visual Features in the Wild","created":"2021-03-02","cited_by_count":198},{"id":"2009.01974","title":"FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning","created":"2020-09-04","cited_by_count":176},{"id":"2008.03606","title":"Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning","created":"2020-08-08","cited_by_count":154},{"id":"1910.14425","title":"On the Convergence of Local Descent Methods in Federated Learning","created":"2019-10-31","cited_by_count":153},{"id":"2003.12862","title":"Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning","created":"2020-03-28","cited_by_count":153},{"id":"2112.09153","title":"An Empirical Investigation of the Role of Pre-training in Lifelong Learning","created":"2021-12-16","cited_by_count":134},{"id":"2003.08082","title":"Federated Visual Classification with Real-World Data Distribution","created":"2020-03-18","cited_by_count":128},{"id":"2106.06047","title":"Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning","created":"2021-06-10","cited_by_count":111},{"id":"2009.07999","title":"Distilled One-Shot Federated Learning","created":"2020-09-17","cited_by_count":109},{"id":"2101.08515","title":"Pre-training without Natural Images","created":"2021-01-21","cited_by_count":100},{"id":"2007.08558","title":"On Robustness and Transferability of Convolutional Neural Networks","created":"2020-07-16","cited_by_count":98},{"id":"1708.01012","title":"On the convergence properties of a $K$-step averaging stochastic gradient descent algorithm for nonconvex optimization","created":"2017-08-03","cited_by_count":92},{"id":"2106.05963","title":"Learning to See by Looking at Noise","created":"2021-06-10","cited_by_count":92},{"id":"1709.01450","title":"The Devil is in the Tails: Fine-grained Classification in the Wild","created":"2017-09-05","cited_by_count":89},{"id":"2104.08815","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","created":"2021-04-18","cited_by_count":85},{"id":"2103.12718","title":"Self-Supervised Pretraining Improves Self-Supervised Pretraining","created":"2021-03-23","cited_by_count":82},{"id":"2001.01920","title":"FedDANE: A Federated Newton-Type Method","created":"2020-01-07","cited_by_count":76},{"id":"1908.05620","title":"Visualizing and Understanding the Effectiveness of BERT","created":"2019-08-15","cited_by_count":67},{"id":"2103.14010","title":"Self-Supervised Training Enhances Online Continual Learning","created":"2021-03-25","cited_by_count":54},{"id":"2205.11506","title":"Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering","created":"2022-05-23","cited_by_count":45},{"id":"2106.07803","title":"SynthASR: Unlocking Synthetic Data for Speech Recognition","created":"2021-06-14","cited_by_count":34},{"id":"2009.07724","title":"SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning","created":"2020-09-16","cited_by_count":32},{"id":"2206.02291","title":"Pretrained Models for Multilingual Federated Learning","created":"2022-06-06","cited_by_count":30},{"id":"2110.03091","title":"Improving Fractal Pre-training","created":"2021-10-06","cited_by_count":26},{"id":"2206.10139","title":"Insights into Pre-training via Simpler Synthetic Tasks","created":"2022-06-21","cited_by_count":26},{"id":"1910.08234","title":"Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating","created":"2019-10-18","cited_by_count":22},{"id":"2005.04828","title":"Pretraining Federated Text Models for Next Word Prediction","created":"2020-05-11","cited_by_count":22},{"id":"2203.05931","title":"FedSyn: Synthetic Data Generation using Federated Learning","created":"2022-03-11","cited_by_count":7}],"next_cursor":null}