{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"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":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1801.09414","title":"CosFace: Large Margin Cosine Loss for Deep Face Recognition","created":"2018-01-29","cited_by_count":971},{"id":"1710.08092","title":"VGGFace2: A dataset for recognising faces across pose and age","created":"2017-10-23","cited_by_count":914},{"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":"1704.08063","title":"SphereFace: Deep Hypersphere Embedding for Face Recognition","created":"2017-04-26","cited_by_count":737},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"1907.09682","title":"Similarity-Preserving Knowledge Distillation","created":"2019-07-23","cited_by_count":516},{"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":"1312.6184","title":"Do Deep Nets Really Need to be Deep?","created":"2013-12-21","cited_by_count":474},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"id":"1904.05835","title":"Variational Information Distillation for Knowledge Transfer","created":"2019-04-11","cited_by_count":324},{"id":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"1904.01802","title":"Correlation Congruence for Knowledge Distillation","created":"2019-04-03","cited_by_count":285},{"id":"1903.04197","title":"Structured Knowledge Distillation for Dense Prediction","created":"2019-03-11","cited_by_count":279},{"id":"1802.04977","title":"Paraphrasing Complex Network: Network Compression via Factor Transfer","created":"2018-02-14","cited_by_count":260},{"id":"1811.03233","title":"Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons","created":"2018-11-08","cited_by_count":238},{"id":"1803.10837","title":"Learning Deep Representations with Probabilistic Knowledge Transfer","created":"2018-03-28","cited_by_count":213},{"id":"1806.04606","title":"Knowledge Distillation by On-the-Fly Native Ensemble","created":"2018-06-12","cited_by_count":186},{"id":"1804.03235","title":"Large scale distributed neural network training through online distillation","created":"2018-04-09","cited_by_count":146},{"id":"2003.13964","title":"Regularizing Class-wise Predictions via Self-knowledge Distillation","created":"2020-03-31","cited_by_count":144},{"id":"1912.00350","title":"Online Knowledge Distillation with Diverse Peers","created":"2019-12-01","cited_by_count":128},{"id":"1812.00123","title":"Snapshot Distillation: Teacher-Student Optimization in One Generation","created":"2018-12-01","cited_by_count":99},{"id":"1811.09030","title":"Data Augmentation using Random Image Cropping and Patching for Deep CNNs","created":"2018-11-22","cited_by_count":88},{"id":"1904.09149","title":"Knowledge Distillation via Route Constrained Optimization","created":"2019-04-19","cited_by_count":75},{"id":"2005.00727","title":"Heterogeneous Knowledge Distillation using Information Flow Modeling","created":"2020-05-02","cited_by_count":73},{"id":"1805.11761","title":"Collaborative Learning for Deep Neural Networks","created":"2018-05-30","cited_by_count":69},{"id":"2003.03622","title":"Explaining Knowledge Distillation by Quantifying the Knowledge","created":"2020-03-07","cited_by_count":66},{"id":"2002.01775","title":"Feature-map-level Online Adversarial Knowledge Distillation","created":"2020-02-05","cited_by_count":62},{"id":"1811.09998","title":"Low-resolution Face Recognition in the Wild via Selective Knowledge Distillation","created":"2018-11-25","cited_by_count":55},{"id":"1812.02425","title":"MEAL: Multi-Model Ensemble via Adversarial Learning","created":"2018-12-06","cited_by_count":52},{"id":"1611.01484","title":"UMDFaces: An Annotated Face Dataset for Training Deep Networks","created":"2016-11-04","cited_by_count":42},{"id":"1809.11130","title":"Channel-wise and Spatial Feature Modulation Network for Single Image Super-Resolution","created":"2018-09-28","cited_by_count":42},{"id":"2009.08453","title":"MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks","created":"2020-09-17","cited_by_count":40},{"id":"1907.06119","title":"Understanding Deep Learning Techniques for Image Segmentation","created":"2019-07-13","cited_by_count":38},{"id":"1601.04153","title":"Studying Very Low Resolution Recognition Using Deep Networks","created":"2016-01-16","cited_by_count":36},{"id":"1805.11529","title":"On Low-Resolution Face Recognition in the Wild: Comparisons and New Techniques","created":"2018-05-29","cited_by_count":34},{"id":"1711.02613","title":"Moonshine: Distilling with Cheap Convolutions","created":"2017-11-07","cited_by_count":25},{"id":"2006.04719","title":"ResKD: Residual-Guided Knowledge Distillation","created":"2020-06-08","cited_by_count":25},{"id":"1708.02337","title":"Unconstrained Face Detection and Open-Set Face Recognition Challenge","created":"2017-08-08","cited_by_count":18},{"id":"1702.02052","title":"Knowledge Adaptation: Teaching to Adapt","created":"2017-02-07","cited_by_count":17},{"id":"1908.01790","title":"Attribute-Guided Coupled GAN for Cross-Resolution Face Recognition","created":"2019-08-05","cited_by_count":12},{"id":"1807.08169","title":"Recent Advances in Deep Learning: An Overview","created":"2018-07-21","cited_by_count":10}],"next_cursor":null}