{"list":"other","total":46,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1607.02533","title":"Adversarial examples in the physical world","created":"2016-07-08","cited_by_count":1769},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"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":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361},{"id":"1907.07484","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","created":"2019-07-17","cited_by_count":336},{"id":"2004.05937","title":"Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks","created":"2020-04-13","cited_by_count":316},{"id":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"2003.02218","title":"The large learning rate phase of deep learning: the catapult mechanism","created":"2020-03-04","cited_by_count":216},{"id":"1806.04606","title":"Knowledge Distillation by On-the-Fly Native Ensemble","created":"2018-06-12","cited_by_count":186},{"id":"2002.05715","title":"Self-Distillation Amplifies Regularization in Hilbert Space","created":"2020-02-13","cited_by_count":173},{"id":"1912.00350","title":"Online Knowledge Distillation with Diverse Peers","created":"2019-12-01","cited_by_count":128},{"id":"2010.05627","title":"Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning","created":"2020-10-12","cited_by_count":126},{"id":"1904.09080","title":"Implicit regularization for deep neural networks driven by an Ornstein-Uhlenbeck like process","created":"2019-04-19","cited_by_count":123},{"id":"2106.06530","title":"Label Noise SGD Provably Prefers Flat Global Minimizers","created":"2021-06-11","cited_by_count":121},{"id":"2002.10365","title":"The Early Phase of Neural Network Training","created":"2020-02-24","cited_by_count":115},{"id":"2106.03746","title":"Efficient Training of Visual Transformers with Small Datasets","created":"2021-06-07","cited_by_count":108},{"id":"2006.12000","title":"Self-Knowledge Distillation with Progressive Refinement of Targets","created":"2020-06-22","cited_by_count":107},{"id":"1812.00123","title":"Snapshot Distillation: Teacher-Student Optimization in One Generation","created":"2018-12-01","cited_by_count":99},{"id":"1902.00744","title":"Asymmetric Valleys: Beyond Sharp and Flat Local Minima","created":"2019-02-02","cited_by_count":90},{"id":"1807.05031","title":"On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length","created":"2018-07-13","cited_by_count":88},{"id":"1907.10107","title":"Lifelong GAN: Continual Learning for Conditional Image Generation","created":"2019-07-23","cited_by_count":78},{"id":"2006.05065","title":"Self-Distillation as Instance-Specific Label Smoothing","created":"2020-06-09","cited_by_count":71},{"id":"2006.04147","title":"Peer Collaborative Learning for Online Knowledge Distillation","created":"2020-06-07","cited_by_count":58},{"id":"1909.08097","title":"Ensemble Knowledge Distillation for Learning Improved and Efficient Networks","created":"2019-09-17","cited_by_count":46},{"id":"2207.10026","title":"Locality Guidance for Improving Vision Transformers on Tiny Datasets","created":"2022-07-20","cited_by_count":33},{"id":"1911.09074","title":"Search to Distill: Pearls are Everywhere but not the Eyes","created":"2019-11-20","cited_by_count":26},{"id":"2110.08532","title":"Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher","created":"2021-10-16","cited_by_count":17},{"id":"2404.00417","title":"Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation","created":"2024-03-30","cited_by_count":16},{"id":"1910.05872","title":"Self-supervised Label Augmentation via Input Transformations","created":"2019-10-14","cited_by_count":15},{"id":"1911.13019","title":"Towards Oracle Knowledge Distillation with Neural Architecture Search","created":"2019-11-29","cited_by_count":13},{"id":"2001.11612","title":"Search for Better Students to Learn Distilled Knowledge","created":"2020-01-30","cited_by_count":11},{"id":"1606.08370","title":"The right time to learn: mechanisms and optimization of spaced learning","created":"2016-06-27","cited_by_count":5}],"next_cursor":null}