{"list":"other","total":76,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"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":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"1710.08092","title":"VGGFace2: A dataset for recognising faces across pose and age","created":"2017-10-23","cited_by_count":914},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1804.03209","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","created":"2018-04-09","cited_by_count":752},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"1810.11910","title":"Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference","created":"2018-10-29","cited_by_count":521},{"id":"1310.1531","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","created":"2013-10-06","cited_by_count":424},{"id":"1403.6382","title":"CNN Features off-the-shelf: an Astounding Baseline for Recognition","created":"2014-03-23","cited_by_count":316},{"id":"2007.10319","title":"MCUNet: Tiny Deep Learning on IoT Devices","created":"2020-07-20","cited_by_count":273},{"id":"1511.05641","title":"Net2Net: Accelerating Learning via Knowledge Transfer","created":"2015-11-18","cited_by_count":250},{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223},{"id":"1802.02871","title":"Online Learning: A Comprehensive Survey","created":"2018-02-08","cited_by_count":205},{"id":"1905.12588","title":"Meta-Learning Representations for Continual Learning","created":"2019-05-29","cited_by_count":189},{"id":"2206.15472","title":"On-Device Training Under 256KB Memory","created":"2022-06-30","cited_by_count":160},{"id":"1603.00748","title":"Continuous Deep Q-Learning with Model-based Acceleration","created":"2016-03-02","cited_by_count":157},{"id":"1711.11294","title":"Towards Accurate Binary Convolutional Neural Network","created":"2017-11-30","cited_by_count":149},{"id":"2006.10901","title":"Sparse GPU Kernels for Deep Learning","created":"2020-06-18","cited_by_count":141},{"id":"2008.06402","title":"SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud","created":"2020-08-14","cited_by_count":112},{"id":"1910.02653","title":"Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization","created":"2019-10-07","cited_by_count":91},{"id":"2002.09571","title":"Learning to Continually Learn","created":"2020-02-21","cited_by_count":84},{"id":"1805.00907","title":"Glow: Graph Lowering Compiler Techniques for Neural Networks","created":"2018-05-02","cited_by_count":75},{"id":"1810.10090","title":"NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision","created":"2018-10-23","cited_by_count":68},{"id":"2002.12418","title":"MNN: A Universal and Efficient Inference Engine","created":"2020-02-27","cited_by_count":65},{"id":"2103.08295","title":"TinyOL: TinyML with Online-Learning on Microcontrollers","created":"2021-03-15","cited_by_count":65},{"id":"1911.00623","title":"On-Device Machine Learning: An Algorithms and Learning Theory Perspective","created":"2019-11-02","cited_by_count":63},{"id":"1711.02017","title":"NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm","created":"2017-11-06","cited_by_count":60},{"id":"2012.10557","title":"Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers","created":"2020-12-19","cited_by_count":58},{"id":"1712.01670","title":"DeepCache: Principled Cache for Mobile Deep Vision","created":"2017-12-01","cited_by_count":57},{"id":"1903.04687","title":"Transfer Adaptation Learning: A Decade Survey","created":"2019-03-12","cited_by_count":52},{"id":"1510.03009","title":"Neural Networks with Few Multiplications","created":"2015-10-11","cited_by_count":48},{"id":"1812.05448","title":"A First Look at Deep Learning Apps on Smartphones","created":"2018-11-08","cited_by_count":47},{"id":"2006.09616","title":"Dynamic Tensor Rematerialization","created":"2020-06-17","cited_by_count":46},{"id":"2110.08450","title":"Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining","created":"2021-10-16","cited_by_count":39},{"id":"2206.07509","title":"Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading","created":"2022-06-15","cited_by_count":29},{"id":"2205.14550","title":"Machine Learning for Microcontroller-Class Hardware: A Review","created":"2022-05-29","cited_by_count":28},{"id":"2207.07697","title":"POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging","created":"2022-07-15","cited_by_count":26},{"id":"1810.00859","title":"Dynamic Sparse Graph for Efficient Deep Learning","created":"2018-10-01","cited_by_count":18},{"id":"2107.14053","title":"Few-Shot and Continual Learning with Attentive Independent Mechanisms","created":"2021-07-29","cited_by_count":13},{"id":"2202.06512","title":"Benchmarking of DL Libraries and Models on Mobile Devices","created":"2022-02-14","cited_by_count":12},{"id":"1905.11722","title":"A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation","created":"2019-05-28","cited_by_count":11},{"id":"2206.12705","title":"p-Meta: Towards On-device Deep Model Adaptation","created":"2022-06-25","cited_by_count":8},{"id":"1905.11533","title":"CGaP: Continuous Growth and Pruning for Efficient Deep Learning","created":"2019-05-27","cited_by_count":3},{"id":"1804.02491","title":"Continuously Constructive Deep Neural Networks","created":"2018-04-07","cited_by_count":2}],"next_cursor":null}