{"list":"other","total":49,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"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":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"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":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"id":"1907.09682","title":"Similarity-Preserving Knowledge Distillation","created":"2019-07-23","cited_by_count":516},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"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":"1805.11604","title":"How Does Batch Normalization Help Optimization?","created":"2018-05-29","cited_by_count":357},{"id":"2002.09437","title":"Calibrating Deep Neural Networks using Focal Loss","created":"2020-02-21","cited_by_count":357},{"id":"1904.01866","title":"A Comprehensive Overhaul of Feature Distillation","created":"2019-04-03","cited_by_count":348},{"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":"1903.04197","title":"Structured Knowledge Distillation for Dense Prediction","created":"2019-03-11","cited_by_count":279},{"id":"2110.07178","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","created":"2021-10-14","cited_by_count":270},{"id":"2205.09310","title":"Mitigating Neural Network Overconfidence with Logit Normalization","created":"2022-05-19","cited_by_count":252},{"id":"1811.03233","title":"Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons","created":"2018-11-08","cited_by_count":238},{"id":"1906.03609","title":"Distilling Object Detectors with Fine-grained Feature Imitation","created":"2019-06-09","cited_by_count":189},{"id":"2012.03236","title":"Cross-Layer Distillation with Semantic Calibration","created":"2020-12-06","cited_by_count":143},{"id":"1908.08962","title":"Well-Read Students Learn Better: On the Importance of Pre-training Compact Models","created":"2019-08-23","cited_by_count":120},{"id":"2305.15712","title":"Knowledge Diffusion for Distillation","created":"2023-05-25","cited_by_count":53},{"id":"2108.09987","title":"Efficient Medical Image Segmentation Based on Knowledge Distillation","created":"2021-08-23","cited_by_count":43},{"id":"2112.04840","title":"Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation","created":"2021-12-09","cited_by_count":40},{"id":"2109.08359","title":"Distilling Linguistic Context for Language Model Compression","created":"2021-09-17","cited_by_count":33},{"id":"2207.10026","title":"Locality Guidance for Improving Vision Transformers on Tiny Datasets","created":"2022-07-20","cited_by_count":33},{"id":"2305.13665","title":"Dual Focal Loss for Calibration","created":"2023-05-23","cited_by_count":33},{"id":"2205.15156","title":"Towards Efficient 3D Object Detection with Knowledge Distillation","created":"2022-05-30","cited_by_count":29},{"id":"2305.10010","title":"AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression","created":"2023-05-17","cited_by_count":26},{"id":"2204.05957","title":"Localization Distillation for Object Detection","created":"2022-04-12","cited_by_count":19},{"id":"2205.11420","title":"LILA-BOTI : Leveraging Isolated Letter Accumulations By Ordering Teacher Insights for Bangla Handwriting Recognition","created":"2022-05-23","cited_by_count":3}],"next_cursor":null}