{"list":"other","total":139,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"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":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":445},{"id":"2001.00326","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","created":"2020-01-02","cited_by_count":416},{"id":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1703.01041","title":"Large-Scale Evolution of Image Classifiers","created":"2017-03-03","cited_by_count":348},{"id":"1902.09635","title":"NAS-Bench-101: Towards Reproducible Neural Architecture Search","created":"2019-02-25","cited_by_count":344},{"id":"1710.09282","title":"A Survey of Model Compression and Acceleration for Deep Neural Networks","created":"2017-10-23","cited_by_count":301},{"id":"1904.07392","title":"NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection","created":"2019-04-16","cited_by_count":291},{"id":"2007.10319","title":"MCUNet: Tiny Deep Learning on IoT Devices","created":"2020-07-20","cited_by_count":273},{"id":"1901.02985","title":"Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation","created":"2019-01-10","cited_by_count":260},{"id":"1902.07638","title":"Random Search and Reproducibility for Neural Architecture Search","created":"2019-02-20","cited_by_count":254},{"id":"2006.04647","title":"Neural Architecture Search without Training","created":"2020-06-08","cited_by_count":244},{"id":"1312.6229","title":"OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks","created":"2013-12-21","cited_by_count":224},{"id":"1708.02182","title":"Regularizing and Optimizing LSTM Language Models","created":"2017-08-07","cited_by_count":205},{"id":"1804.09081","title":"Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution","created":"2018-04-24","cited_by_count":153},{"id":"1804.03230","title":"NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications","created":"2018-04-09","cited_by_count":147},{"id":"2005.09629","title":"Improved Noisy Student Training for Automatic Speech Recognition","created":"2020-05-19","cited_by_count":141},{"id":"2005.14187","title":"HAT: Hardware-Aware Transformers for Efficient Natural Language Processing","created":"2020-05-28","cited_by_count":136},{"id":"1812.00090","title":"Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search","created":"2018-11-30","cited_by_count":125},{"id":"2006.08509","title":"APQ: Joint Search for Network Architecture, Pruning and Quantization Policy","created":"2020-06-15","cited_by_count":99},{"id":"2009.00437","title":"NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size","created":"2020-08-28","cited_by_count":98},{"id":"1711.06798","title":"MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks","created":"2017-11-18","cited_by_count":94},{"id":"1908.03835","title":"AutoGAN: Neural Architecture Search for Generative Adversarial Networks","created":"2019-08-11","cited_by_count":94},{"id":"1904.02877","title":"Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours","created":"2019-04-05","cited_by_count":87},{"id":"1911.10695","title":"When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks","created":"2019-11-25","cited_by_count":87},{"id":"2001.08565","title":"Channel Pruning via Automatic Structure Search","created":"2020-01-23","cited_by_count":85},{"id":"1905.09717","title":"Network Pruning via Transformable Architecture Search","created":"2019-05-23","cited_by_count":80},{"id":"1812.08934","title":"ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation","created":"2018-12-21","cited_by_count":76},{"id":"2007.10396","title":"NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search","created":"2020-07-20","cited_by_count":76},{"id":"1905.01392","title":"A Survey on Neural Architecture Search","created":"2019-05-04","cited_by_count":71},{"id":"2008.06120","title":"Can weight sharing outperform random architecture search? An investigation with TuNAS","created":"2020-08-13","cited_by_count":68},{"id":"1901.07261","title":"Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search","created":"2019-01-22","cited_by_count":66},{"id":"2001.10422","title":"NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search","created":"2020-01-28","cited_by_count":64},{"id":"2005.05859","title":"Neural Architecture Transfer","created":"2020-05-12","cited_by_count":60},{"id":"2006.07116","title":"NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processing","created":"2020-06-12","cited_by_count":60},{"id":"2004.14525","title":"MobileDets: Searching for Object Detection Architectures for Mobile Accelerators","created":"2020-04-30","cited_by_count":55},{"id":"2010.14246","title":"$\\mu$NAS: Constrained Neural Architecture Search for Microcontrollers","created":"2020-10-27","cited_by_count":55},{"id":"1905.12107","title":"SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers","created":"2019-05-28","cited_by_count":52},{"id":"2008.10292","title":"Automated Search for Resource-Efficient Branched Multi-Task Networks","created":"2020-08-24","cited_by_count":51},{"id":"1907.04650","title":"Hardware/Software Co-Exploration of Neural Architectures","created":"2019-07-06","cited_by_count":50},{"id":"1904.04421","title":"FPGA/DNN Co-Design: An Efficient Design Methodology for IoT Intelligence on the Edge","created":"2019-04-09","cited_by_count":48},{"id":"1909.08097","title":"Ensemble Knowledge Distillation for Learning Improved and Efficient Networks","created":"2019-09-17","cited_by_count":46},{"id":"2002.03794","title":"The Deep Learning Compiler: A Comprehensive Survey","created":"2020-02-06","cited_by_count":46},{"id":"2002.04116","title":"Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks","created":"2020-02-10","cited_by_count":43},{"id":"1810.10804","title":"Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells","created":"2018-10-25","cited_by_count":39},{"id":"1903.03777","title":"Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search","created":"2019-03-09","cited_by_count":39},{"id":"1901.11211","title":"Accuracy vs. Efficiency: Achieving Both through FPGA-Implementation Aware Neural Architecture Search","created":"2019-01-31","cited_by_count":38},{"id":"1906.08031","title":"XNAS: Neural Architecture Search with Expert Advice","created":"2019-06-19","cited_by_count":35},{"id":"1804.04849","title":"The unreasonable effectiveness of the forget gate","created":"2018-04-13","cited_by_count":34},{"id":"1910.14488","title":"NAT: Neural Architecture Transformer for Accurate and Compact Architectures","created":"2019-10-31","cited_by_count":33},{"id":"1911.00139","title":"Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Accelerators","created":"2019-10-31","cited_by_count":32},{"id":"2007.10026","title":"Search What You Want: Barrier Panelty NAS for Mixed Precision Quantization","created":"2020-07-20","cited_by_count":32},{"id":"1908.01748","title":"SqueezeNAS: Fast neural architecture search for faster semantic segmentation","created":"2019-08-05","cited_by_count":31},{"id":"2002.05022","title":"Best of Both Worlds: AutoML Codesign of a CNN and its Hardware Accelerator","created":"2020-02-11","cited_by_count":30},{"id":"2003.02838","title":"Accelerator-aware Neural Network Design using AutoML","created":"2020-03-05","cited_by_count":30},{"id":"1906.02817","title":"V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation","created":"2019-06-06","cited_by_count":28},{"id":"2005.06821","title":"A Semi-Supervised Assessor of Neural Architectures","created":"2020-05-14","cited_by_count":28},{"id":"1910.06961","title":"Tiny Video Networks","created":"2019-10-15","cited_by_count":27},{"id":"2007.04356","title":"Journey Towards Tiny Perceptual Super-Resolution","created":"2020-07-08","cited_by_count":27},{"id":"1901.01074","title":"Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search","created":"2019-01-04","cited_by_count":24},{"id":"1712.03351","title":"Peephole: Predicting Network Performance Before Training","created":"2017-12-09","cited_by_count":23},{"id":"1811.01567","title":"You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization","created":"2018-11-05","cited_by_count":23},{"id":"1910.11609","title":"Fast Hardware-Aware Neural Architecture Search","created":"2019-10-25","cited_by_count":23},{"id":"2004.01961","title":"Neural Architecture Search for Lightweight Non-Local Networks","created":"2020-04-04","cited_by_count":23},{"id":"2007.09087","title":"Standing on the Shoulders of Giants: Hardware and Neural Architecture Co-Search with Hot Start","created":"2020-07-17","cited_by_count":22},{"id":"2005.06305","title":"Binarizing MobileNet via Evolution-based Searching","created":"2020-05-13","cited_by_count":21},{"id":"2008.05314","title":"TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Search","created":"2020-08-12","cited_by_count":21},{"id":"1711.02846","title":"Intriguing Properties of Adversarial Examples","created":"2017-11-08","cited_by_count":20},{"id":"1910.03103","title":"Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent","created":"2019-10-07","cited_by_count":18},{"id":"1911.00105","title":"On Neural Architecture Search for Resource-Constrained Hardware Platforms","created":"2019-10-31","cited_by_count":18},{"id":"1908.11450","title":"Neural Network Inference on Mobile SoCs","created":"2019-08-24","cited_by_count":17},{"id":"2008.08476","title":"NASCaps: A Framework for Neural Architecture Search to Optimize the Accuracy and Hardware Efficiency of Convolutional Capsule Networks","created":"2020-08-19","cited_by_count":16},{"id":"2009.06237","title":"DANCE: Differentiable Accelerator/Network Co-Exploration","created":"2020-09-14","cited_by_count":16},{"id":"1806.07912","title":"Resource-Efficient Neural Architect","created":"2018-06-12","cited_by_count":14}],"next_cursor":"100"}