{"list":"other","total":37,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"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":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"1905.08094","title":"Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation","created":"2019-05-17","cited_by_count":497},{"id":"2007.00151","title":"Early-Learning Regularization Prevents Memorization of Noisy Labels","created":"2020-06-30","cited_by_count":416},{"id":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"id":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"1511.03643","title":"Unifying distillation and privileged information","created":"2015-11-11","cited_by_count":233},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"2002.05715","title":"Self-Distillation Amplifies Regularization in Hilbert Space","created":"2020-02-13","cited_by_count":173},{"id":"1903.11680","title":"Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks","created":"2019-03-27","cited_by_count":159},{"id":"1804.03235","title":"Large scale distributed neural network training through online distillation","created":"2018-04-09","cited_by_count":146},{"id":"2010.02666","title":"Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation","created":"2020-10-06","cited_by_count":145},{"id":"1706.04859","title":"Sobolev Training for Neural Networks","created":"2017-06-15","cited_by_count":143},{"id":"1712.04440","title":"Data Distillation: Towards Omni-Supervised Learning","created":"2017-12-12","cited_by_count":126},{"id":"2002.03532","title":"Understanding and Improving Knowledge Distillation","created":"2020-02-10","cited_by_count":83},{"id":"2006.05065","title":"Self-Distillation as Instance-Specific Label Smoothing","created":"2020-06-09","cited_by_count":71},{"id":"2006.00555","title":"Transferring Inductive Biases through Knowledge Distillation","created":"2020-05-31","cited_by_count":41},{"id":"2012.02909","title":"What Makes a \"Good\" Data Augmentation in Knowledge Distillation -- A Statistical Perspective","created":"2020-12-05","cited_by_count":35},{"id":"2010.10090","title":"Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher","created":"2020-10-20","cited_by_count":33},{"id":"1910.01255","title":"Distillation $\\approx$ Early Stopping? Harvesting Dark Knowledge Utilizing Anisotropic Information Retrieval For Overparameterized Neural Network","created":"2019-10-02","cited_by_count":28},{"id":"2006.01683","title":"Channel Distillation: Channel-Wise Attention for Knowledge Distillation","created":"2020-06-02","cited_by_count":21},{"id":"2210.06711","title":"Weighted Distillation with Unlabeled Examples","created":"2022-10-13","cited_by_count":13},{"id":"2006.16589","title":"On the Demystification of Knowledge Distillation: A Residual Network Perspective","created":"2020-06-30","cited_by_count":1}],"next_cursor":null}