{"list":"other","total":58,"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":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"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":"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":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"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":"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":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"id":"1904.01866","title":"A Comprehensive Overhaul of Feature Distillation","created":"2019-04-03","cited_by_count":348},{"id":"1904.05835","title":"Variational Information Distillation for Knowledge Transfer","created":"2019-04-11","cited_by_count":324},{"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":"2010.01809","title":"Long-tailed Recognition by Routing Diverse Distribution-Aware Experts","created":"2020-10-05","cited_by_count":271},{"id":"1802.04977","title":"Paraphrasing Complex Network: Network Compression via Factor Transfer","created":"2018-02-14","cited_by_count":260},{"id":"2009.12991","title":"Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect","created":"2020-09-28","cited_by_count":256},{"id":"1602.05352","title":"Recommendations as Treatments: Debiasing Learning and Evaluation","created":"2016-02-17","cited_by_count":248},{"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":"1708.06977","title":"Incremental Learning of Object Detectors without Catastrophic Forgetting","created":"2017-08-23","cited_by_count":208},{"id":"1906.03609","title":"Distilling Object Detectors with Fine-grained Feature Imitation","created":"2019-06-09","cited_by_count":189},{"id":"2012.00321","title":"Disentangling Label Distribution for Long-tailed Visual Recognition","created":"2020-12-01","cited_by_count":172},{"id":"2003.13964","title":"Regularizing Class-wise Predictions via Self-knowledge Distillation","created":"2020-03-31","cited_by_count":144},{"id":"2006.07114","title":"Knowledge Distillation Meets Self-Supervision","created":"2020-06-12","cited_by_count":142},{"id":"2103.01737","title":"Distilling Causal Effect of Data in Class-Incremental Learning","created":"2021-03-02","cited_by_count":117},{"id":"1805.08206","title":"Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers","created":"2018-05-21","cited_by_count":113},{"id":"2003.13942","title":"Spatio-Temporal Graph for Video Captioning with Knowledge Distillation","created":"2020-03-31","cited_by_count":109},{"id":"2002.11566","title":"Object Relational Graph with Teacher-Recommended Learning for Video Captioning","created":"2020-02-26","cited_by_count":107},{"id":"2006.12000","title":"Self-Knowledge Distillation with Progressive Refinement of Targets","created":"2020-06-22","cited_by_count":107},{"id":"1903.04688","title":"Knowledge Adaptation for Efficient Semantic Segmentation","created":"2019-03-12","cited_by_count":105},{"id":"1812.00123","title":"Snapshot Distillation: Teacher-Student Optimization in One Generation","created":"2018-12-01","cited_by_count":99},{"id":"2009.08825","title":"Densely Guided Knowledge Distillation using Multiple Teacher Assistants","created":"2020-09-18","cited_by_count":83},{"id":"1904.09149","title":"Knowledge Distillation via Route Constrained Optimization","created":"2019-04-19","cited_by_count":75},{"id":"1804.05938","title":"Unbiased Learning to Rank with Unbiased Propensity Estimation","created":"2018-04-16","cited_by_count":61},{"id":"1812.02699","title":"Online Model Distillation for Efficient Video Inference","created":"2018-12-06","cited_by_count":60},{"id":"2110.15255","title":"Self-Supervised Learning Disentangled Group Representation as Feature","created":"2021-10-28","cited_by_count":47},{"id":"2103.08273","title":"Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation","created":"2021-03-15","cited_by_count":46},{"id":"1712.00108","title":"Graph Distillation for Action Detection with Privileged Modalities","created":"2017-11-30","cited_by_count":35},{"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":"2111.01026","title":"Introspective Distillation for Robust Question Answering","created":"2021-11-01","cited_by_count":25},{"id":"1808.06581","title":"The Deconfounded Recommender: A Causal Inference Approach to Recommendation","created":"2018-08-20","cited_by_count":19},{"id":"1812.03631","title":"Spatial Knowledge Distillation to aid Visual Reasoning","created":"2018-12-10","cited_by_count":5}],"next_cursor":null}