{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"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":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"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":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"1312.6184","title":"Do Deep Nets Really Need to be Deep?","created":"2013-12-21","cited_by_count":474},{"id":"2006.04388","title":"Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection","created":"2020-06-08","cited_by_count":409},{"id":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"1904.01866","title":"A Comprehensive Overhaul of Feature Distillation","created":"2019-04-03","cited_by_count":348},{"id":"1602.04433","title":"Unsupervised Domain Adaptation with Residual Transfer Networks","created":"2016-02-14","cited_by_count":341},{"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":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"1511.03643","title":"Unifying distillation and privileged information","created":"2015-11-11","cited_by_count":233},{"id":"1811.10959","title":"Dataset Distillation","created":"2018-11-27","cited_by_count":230},{"id":"1912.12854","title":"Pareto Multi-Task Learning","created":"2019-12-30","cited_by_count":224},{"id":"1609.02132","title":"UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory","created":"2016-09-07","cited_by_count":200},{"id":"1906.03609","title":"Distilling Object Detectors with Fine-grained Feature Imitation","created":"2019-06-09","cited_by_count":189},{"id":"1806.04606","title":"Knowledge Distillation by On-the-Fly Native Ensemble","created":"2018-06-12","cited_by_count":186},{"id":"2001.01536","title":"Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification","created":"2020-01-06","cited_by_count":175},{"id":"1511.06530","title":"Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications","created":"2015-11-20","cited_by_count":162},{"id":"2007.01154","title":"Federated Learning with Compression: Unified Analysis and Sharp Guarantees","created":"2020-07-02","cited_by_count":160},{"id":"1712.04440","title":"Data Distillation: Towards Omni-Supervised Learning","created":"2017-12-12","cited_by_count":126},{"id":"2103.02340","title":"General Instance Distillation for Object Detection","created":"2021-03-03","cited_by_count":114},{"id":"1903.04688","title":"Knowledge Adaptation for Efficient Semantic Segmentation","created":"2019-03-12","cited_by_count":105},{"id":"1711.05852","title":"Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy","created":"2017-11-15","cited_by_count":101},{"id":"1612.07695","title":"MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving","created":"2016-12-22","cited_by_count":90},{"id":"1909.04972","title":"WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection","created":"2019-09-11","cited_by_count":51},{"id":"2011.02367","title":"Federated Knowledge Distillation","created":"2020-11-04","cited_by_count":51},{"id":"1911.03462","title":"Knowledge Distillation for Incremental Learning in Semantic Segmentation","created":"2019-11-08","cited_by_count":40},{"id":"1904.05878","title":"Knowledge Flow: Improve Upon Your Teachers","created":"2019-04-11","cited_by_count":36},{"id":"1810.08476","title":"Improving Fast Segmentation With Teacher-student Learning","created":"2018-10-19","cited_by_count":34},{"id":"2001.02223","title":"Dynamic Task Weighting Methods for Multi-task Networks in Autonomous Driving Systems","created":"2020-01-07","cited_by_count":34},{"id":"1709.06030","title":"N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learning","created":"2017-09-18","cited_by_count":33},{"id":"1801.07365","title":"Learning to Prune Filters in Convolutional Neural Networks","created":"2018-01-23","cited_by_count":25},{"id":"1908.03884","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","created":"2019-08-11","cited_by_count":23},{"id":"1911.03080","title":"Deep geometric knowledge distillation with graphs","created":"2019-11-08","cited_by_count":21},{"id":"1804.10069","title":"Better and Faster: Knowledge Transfer from Multiple Self-supervised Learning Tasks via Graph Distillation for Video Classification","created":"2018-04-26","cited_by_count":20},{"id":"1911.04931","title":"Efficient Fair Principal Component Analysis","created":"2019-11-12","cited_by_count":20},{"id":"1901.05808","title":"AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Driving","created":"2019-01-17","cited_by_count":19},{"id":"1902.00383","title":"Learnable Embedding Space for Efficient Neural Architecture Compression","created":"2019-02-01","cited_by_count":10},{"id":"1911.05700","title":"Graph Representation Learning via Multi-task Knowledge Distillation","created":"2019-11-11","cited_by_count":8},{"id":"2104.01634","title":"Pareto Efficient Fairness in Supervised Learning: From Extraction to Tracing","created":"2021-04-04","cited_by_count":8}],"next_cursor":null}