{"list":"other","total":63,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"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":"2001.05566","title":"Image Segmentation Using Deep Learning: A Survey","created":"2020-01-15","cited_by_count":660},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"1806.08342","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","created":"2018-06-21","cited_by_count":521},{"id":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479},{"id":"1906.04721","title":"Data-Free Quantization Through Weight Equalization and Bias Correction","created":"2019-06-11","cited_by_count":336},{"id":"2004.12993","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","created":"2020-04-27","cited_by_count":332},{"id":"2006.04152","title":"BERT Loses Patience: Fast and Robust Inference with Early Exit","created":"2020-06-07","cited_by_count":273},{"id":"2001.00281","title":"ZeroQ: A Novel Zero Shot Quantization Framework","created":"2020-01-01","cited_by_count":269},{"id":"1910.10073","title":"Depth-Adaptive Transformer","created":"2019-10-22","cited_by_count":236},{"id":"2004.02178","title":"FastBERT: a Self-distilling BERT with Adaptive Inference Time","created":"2020-04-05","cited_by_count":226},{"id":"1902.06822","title":"Low-bit Quantization of Neural Networks for Efficient Inference","created":"2019-02-18","cited_by_count":193},{"id":"2004.09602","title":"Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation","created":"2020-04-20","cited_by_count":188},{"id":"1702.08502","title":"Understanding Convolution for Semantic Segmentation","created":"2017-02-27","cited_by_count":168},{"id":"1901.09504","title":"Improving Neural Network Quantization without Retraining using Outlier Channel Splitting","created":"2019-01-28","cited_by_count":151},{"id":"2003.07326","title":"Resolution Adaptive Networks for Efficient Inference","created":"2020-03-16","cited_by_count":146},{"id":"2004.07320","title":"Training with Quantization Noise for Extreme Model Compression","created":"2020-04-15","cited_by_count":145},{"id":"1709.01921","title":"Distributed Deep Neural Networks over the Cloud, the Edge and End Devices","created":"2017-09-06","cited_by_count":120},{"id":"1907.08349","title":"Convergence of Edge Computing and Deep Learning: A Comprehensive Survey","created":"2019-07-19","cited_by_count":120},{"id":"2103.04505","title":"Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges","created":"2021-03-08","cited_by_count":115},{"id":"2008.06402","title":"SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud","created":"2020-08-14","cited_by_count":112},{"id":"2008.05000","title":"Degree-Quant: Quantization-Aware Training for Graph Neural Networks","created":"2020-08-11","cited_by_count":96},{"id":"1910.14315","title":"BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems","created":"2019-10-31","cited_by_count":95},{"id":"2006.10518","title":"Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming","created":"2020-06-14","cited_by_count":92},{"id":"1908.00080","title":"Machine Learning at the Network Edge: A Survey","created":"2019-07-31","cited_by_count":84},{"id":"1801.08618","title":"JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services","created":"2018-01-25","cited_by_count":80},{"id":"2002.00104","title":"Post-Training Piecewise Linear Quantization for Deep Neural Networks","created":"2020-01-31","cited_by_count":79},{"id":"1909.00560","title":"Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence","created":"2019-09-02","cited_by_count":76},{"id":"2004.12814","title":"Why should we add early exits to neural networks?","created":"2020-04-27","cited_by_count":70},{"id":"1902.01000","title":"BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services","created":"2019-02-04","cited_by_count":68},{"id":"1908.06294","title":"Improved Techniques for Training Adaptive Deep Networks","created":"2019-08-17","cited_by_count":66},{"id":"1806.07840","title":"Edge Intelligence: On-Demand Deep Learning Model Co-Inference with Device-Edge Synergy","created":"2018-06-20","cited_by_count":51},{"id":"1802.03931","title":"Deep feature compression for collaborative object detection","created":"2018-02-12","cited_by_count":48},{"id":"1902.01917","title":"Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorization","created":"2019-02-05","cited_by_count":45},{"id":"2106.05409","title":"Zero Time Waste: Recycling Predictions in Early Exit Neural Networks","created":"2021-06-09","cited_by_count":39},{"id":"1907.04523","title":"Dual Dynamic Inference: Enabling More Efficient, Adaptive and Controllable Deep Inference","created":"2019-07-10","cited_by_count":31},{"id":"2108.11898","title":"Supervised Compression for Resource-Constrained Edge Computing Systems","created":"2021-08-21","cited_by_count":31},{"id":"2006.16581","title":"Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images","created":"2020-06-30","cited_by_count":28},{"id":"2007.15818","title":"Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks","created":"2020-07-31","cited_by_count":28},{"id":"2201.02693","title":"BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing","created":"2022-01-07","cited_by_count":28},{"id":"2010.04354","title":"Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search","created":"2020-10-09","cited_by_count":26},{"id":"2206.06501","title":"Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training","created":"2022-06-13","cited_by_count":26},{"id":"2011.14808","title":"Bringing AI To Edge: From Deep Learning's Perspective","created":"2020-11-25","cited_by_count":24},{"id":"1810.05488","title":"Quantization for Rapid Deployment of Deep Neural Networks","created":"2018-10-12","cited_by_count":20},{"id":"1812.06426","title":"Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge","created":"2018-12-16","cited_by_count":20},{"id":"2005.02534","title":"The Cascade Transformer: an Application for Efficient Answer Sentence Selection","created":"2020-05-05","cited_by_count":20},{"id":"2105.06002","title":"Lightweight compression of neural network feature tensors for collaborative intelligence","created":"2021-05-12","cited_by_count":17},{"id":"2105.11010","title":"Post-Training Sparsity-Aware Quantization","created":"2021-05-23","cited_by_count":17},{"id":"2002.07036","title":"Back-and-Forth prediction for deep tensor compression","created":"2020-02-14","cited_by_count":16},{"id":"2203.08875","title":"SC2 Benchmark: Supervised Compression for Split Computing","created":"2022-03-16","cited_by_count":15},{"id":"2102.06365","title":"Dynamic Precision Analog Computing for Neural Networks","created":"2021-02-12","cited_by_count":12},{"id":"2102.06366","title":"Confounding Tradeoffs for Neural Network Quantization","created":"2021-02-12","cited_by_count":9},{"id":"2206.14322","title":"An Empirical Study of Challenges in Converting Deep Learning Models","created":"2022-06-28","cited_by_count":8},{"id":"2007.13312","title":"Split Computing for Complex Object Detectors: Challenges and Preliminary Results","created":"2020-07-27","cited_by_count":7},{"id":"2105.00591","title":"Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation","created":"2021-05-03","cited_by_count":6},{"id":"2210.15621","title":"Class Based Thresholding in Early Exit Semantic Segmentation Networks","created":"2022-10-27","cited_by_count":5},{"id":"2306.12185","title":"Adaptive DNN Surgery for Selfish Inference Acceleration with On-demand Edge Resource","created":"2023-06-21","cited_by_count":2},{"id":"2105.02613","title":"Challenges and Obstacles Towards Deploying Deep Learning Models on Mobile Devices","created":"2021-05-06","cited_by_count":1}],"next_cursor":null}