{"list":"other","total":46,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"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":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"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":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"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":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"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":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"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":"1312.6184","title":"Do Deep Nets Really Need to be Deep?","created":"2013-12-21","cited_by_count":474},{"id":"1904.05835","title":"Variational Information Distillation for Knowledge Transfer","created":"2019-04-11","cited_by_count":324},{"id":"1412.0233","title":"The Loss Surfaces of Multilayer Networks","created":"2014-11-30","cited_by_count":280},{"id":"1802.04977","title":"Paraphrasing Complex Network: Network Compression via Factor Transfer","created":"2018-02-14","cited_by_count":260},{"id":"1908.02288","title":"BCN20000: Dermoscopic Lesions in the Wild","created":"2019-08-06","cited_by_count":225},{"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":"1905.00076","title":"Ensemble Distribution Distillation","created":"2019-04-30","cited_by_count":158},{"id":"2012.03236","title":"Cross-Layer Distillation with Semantic Calibration","created":"2020-12-06","cited_by_count":143},{"id":"2006.07114","title":"Knowledge Distillation Meets Self-Supervision","created":"2020-06-12","cited_by_count":142},{"id":"1912.00350","title":"Online Knowledge Distillation with Diverse Peers","created":"2019-12-01","cited_by_count":128},{"id":"1803.00443","title":"Knowledge Transfer with Jacobian Matching","created":"2018-03-01","cited_by_count":76},{"id":"2002.01775","title":"Feature-map-level Online Adversarial Knowledge Distillation","created":"2020-02-05","cited_by_count":62},{"id":"2006.04147","title":"Peer Collaborative Learning for Online Knowledge Distillation","created":"2020-06-07","cited_by_count":58},{"id":"1811.09998","title":"Low-resolution Face Recognition in the Wild via Selective Knowledge Distillation","created":"2018-11-25","cited_by_count":55},{"id":"2305.15712","title":"Knowledge Diffusion for Distillation","created":"2023-05-25","cited_by_count":53},{"id":"1904.09058","title":"Feature Fusion for Online Mutual Knowledge Distillation","created":"2019-04-19","cited_by_count":40},{"id":"1911.09074","title":"Search to Distill: Pearls are Everywhere but not the Eyes","created":"2019-11-20","cited_by_count":26},{"id":"2108.05507","title":"Distilling Holistic Knowledge with Graph Neural Networks","created":"2021-08-12","cited_by_count":26},{"id":"2206.06561","title":"FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks","created":"2022-06-14","cited_by_count":23},{"id":"2010.00795","title":"Online Knowledge Distillation via Multi-branch Diversity Enhancement","created":"2020-10-02","cited_by_count":21},{"id":"2008.09958","title":"Matching Guided Distillation","created":"2020-08-23","cited_by_count":18},{"id":"2203.11490","title":"SSD-KD: A Self-supervised Diverse Knowledge Distillation Method for Lightweight Skin Lesion Classification Using Dermoscopic Images","created":"2022-03-22","cited_by_count":12},{"id":"2307.00534","title":"Shared Growth of Graph Neural Networks via Prompted Free-direction Knowledge Distillation","created":"2023-07-02","cited_by_count":1}],"next_cursor":null}