{"list":"other","total":110,"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":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"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":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"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":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"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":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1404.7828","title":"Deep Learning in Neural Networks: An Overview","created":"2014-04-30","cited_by_count":770},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"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":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"1312.6184","title":"Do Deep Nets Really Need to be Deep?","created":"2013-12-21","cited_by_count":474},{"id":"1703.09039","title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","created":"2017-03-27","cited_by_count":434},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"id":"1911.11907","title":"GhostNet: More Features from Cheap Operations","created":"2019-11-27","cited_by_count":410},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1904.05835","title":"Variational Information Distillation for Knowledge Transfer","created":"2019-04-11","cited_by_count":324},{"id":"1404.0736","title":"Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation","created":"2014-04-02","cited_by_count":306},{"id":"1904.01802","title":"Correlation Congruence for Knowledge Distillation","created":"2019-04-03","cited_by_count":285},{"id":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"1811.03233","title":"Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons","created":"2018-11-08","cited_by_count":238},{"id":"1511.03643","title":"Unifying distillation and privileged information","created":"2015-11-11","cited_by_count":233},{"id":"1608.04493","title":"Dynamic Network Surgery for Efficient DNNs","created":"2016-08-16","cited_by_count":233},{"id":"1905.10083","title":"Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing","created":"2019-05-24","cited_by_count":228},{"id":"1306.0543","title":"Predicting Parameters in Deep Learning","created":"2013-06-03","cited_by_count":224},{"id":"1607.03250","title":"Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures","created":"2016-07-12","cited_by_count":221},{"id":"1512.06473","title":"Quantized Convolutional Neural Networks for Mobile Devices","created":"2015-12-21","cited_by_count":215},{"id":"1605.04711","title":"Ternary Weight Networks","created":"2016-05-16","cited_by_count":204},{"id":"1412.6115","title":"Compressing Deep Convolutional Networks using Vector Quantization","created":"2014-12-18","cited_by_count":195},{"id":"1707.01213","title":"Data-Driven Sparse Structure Selection for Deep Neural Networks","created":"2017-07-05","cited_by_count":181},{"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":"1911.09464","title":"Quantization Networks","created":"2019-11-21","cited_by_count":153},{"id":"1910.05316","title":"Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing","created":"2019-10-04","cited_by_count":152},{"id":"1804.03235","title":"Large scale distributed neural network training through online distillation","created":"2018-04-09","cited_by_count":146},{"id":"1903.09291","title":"Towards Optimal Structured CNN Pruning via Generative Adversarial Learning","created":"2019-03-22","cited_by_count":146},{"id":"1611.05128","title":"Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning","created":"2016-11-16","cited_by_count":134},{"id":"1711.09224","title":"CondenseNet: An Efficient DenseNet using Learned Group Convolutions","created":"2017-11-25","cited_by_count":122},{"id":"1702.00953","title":"Deep Learning with Low Precision by Half-wave Gaussian Quantization","created":"2017-02-03","cited_by_count":117},{"id":"1903.04688","title":"Knowledge Adaptation for Efficient Semantic Segmentation","created":"2019-03-12","cited_by_count":105},{"id":"1511.06067","title":"Convolutional neural networks with low-rank regularization","created":"2015-11-19","cited_by_count":103},{"id":"1711.08141","title":"Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions","created":"2017-11-22","cited_by_count":93},{"id":"1809.07857","title":"In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning","created":"2018-09-19","cited_by_count":80},{"id":"1611.01600","title":"Loss-aware Binarization of Deep Networks","created":"2016-11-05","cited_by_count":56},{"id":"1612.01051","title":"SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving","created":"2016-12-04","cited_by_count":55},{"id":"1612.00694","title":"ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA","created":"2016-12-01","cited_by_count":52},{"id":"1812.02425","title":"MEAL: Multi-Model Ensemble via Adversarial Learning","created":"2018-12-06","cited_by_count":52},{"id":"1612.01543","title":"Towards the Limit of Network Quantization","created":"2016-12-05","cited_by_count":50},{"id":"1904.03624","title":"Learning Metrics from Teachers: Compact Networks for Image Embedding","created":"2019-04-07","cited_by_count":39},{"id":"1904.05878","title":"Knowledge Flow: Improve Upon Your Teachers","created":"2019-04-11","cited_by_count":36},{"id":"2010.03954","title":"A Survey on Deep Neural Network Compression: Challenges, Overview, and Solutions","created":"2020-10-05","cited_by_count":32},{"id":"1907.02226","title":"Graph-based Knowledge Distillation by Multi-head Attention Network","created":"2019-07-04","cited_by_count":31},{"id":"1411.4229","title":"Efficient and Accurate Approximations of Nonlinear Convolutional Networks","created":"2014-11-16","cited_by_count":30},{"id":"1708.06128","title":"Revisiting knowledge transfer for training object class detectors","created":"2017-08-21","cited_by_count":26},{"id":"1711.02613","title":"Moonshine: Distilling with Cheap Convolutions","created":"2017-11-07","cited_by_count":25},{"id":"2004.12817","title":"LightPAFF: A Two-Stage Distillation Framework for Pre-training and Fine-tuning","created":"2020-04-27","cited_by_count":25},{"id":"1706.01215","title":"DeepIoT: Compressing Deep Neural Network Structures for Sensing Systems with a Compressor-Critic Framework","created":"2017-06-05","cited_by_count":22},{"id":"1906.03951","title":"SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models","created":"2019-05-27","cited_by_count":22},{"id":"1708.01001","title":"Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization","created":"2017-08-03","cited_by_count":21},{"id":"1907.11093","title":"SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV Applications","created":"2019-07-25","cited_by_count":21},{"id":"1906.00245","title":"Blockchain for Internet of Things: A Survey","created":"2019-06-01","cited_by_count":15},{"id":"2003.04289","title":"Knowledge distillation via adaptive instance normalization","created":"2020-03-09","cited_by_count":14},{"id":"2010.09680","title":"A Survey of Machine Learning Techniques in Adversarial Image Forensics","created":"2020-10-19","cited_by_count":14},{"id":"1706.02393","title":"ShiftCNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural Networks","created":"2017-06-07","cited_by_count":13},{"id":"1907.11804","title":"Memory- and Communication-Aware Model Compression for Distributed Deep Learning Inference on IoT","created":"2019-07-26","cited_by_count":13},{"id":"1805.10692","title":"Compact and Computationally Efficient Representation of Deep Neural Networks","created":"2018-05-27","cited_by_count":11},{"id":"1901.06588","title":"Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep Networks","created":"2019-01-19","cited_by_count":11},{"id":"1906.02876","title":"Compressing RNNs for IoT devices by 15-38x using Kronecker Products","created":"2019-06-07","cited_by_count":11},{"id":"2002.09168","title":"Residual Knowledge Distillation","created":"2020-02-21","cited_by_count":11},{"id":"1801.02077","title":"Handover Control in Wireless Systems via Asynchronous Multi-User Deep Reinforcement Learning","created":"2018-01-06","cited_by_count":9},{"id":"1912.02057","title":"RTN: Reparameterized Ternary Network","created":"2019-12-04","cited_by_count":9},{"id":"1911.05700","title":"Graph Representation Learning via Multi-task Knowledge Distillation","created":"2019-11-11","cited_by_count":8},{"id":"2001.05868","title":"Filter Grafting for Deep Neural Networks","created":"2020-01-15","cited_by_count":8},{"id":"1710.11001","title":"A Comprehensive Survey on Fog Computing: State-of-the-art and Research Challenges","created":"2017-10-30","cited_by_count":7},{"id":"1711.04686","title":"Weightless: Lossy Weight Encoding For Deep Neural Network Compression","created":"2017-11-13","cited_by_count":7},{"id":"1812.02375","title":"DNQ: Dynamic Network Quantization","created":"2018-12-06","cited_by_count":7},{"id":"1901.05107","title":"Actions Speak Louder Than (Pass)words: Passive Authentication of Smartphone Users via Deep Temporal Features","created":"2019-01-16","cited_by_count":7},{"id":"2005.03948","title":"Layer-wise training convolutional neural networks with smaller filters for human activity recognition using wearable sensors","created":"2020-05-08","cited_by_count":7},{"id":"1712.01721","title":"Automated Pruning for Deep Neural Network Compression","created":"2017-12-05","cited_by_count":6},{"id":"2003.09855","title":"TanhExp: A Smooth Activation Function with High Convergence Speed for Lightweight Neural Networks","created":"2020-03-22","cited_by_count":6}],"next_cursor":"100"}