{"list":"other","total":272,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"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":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"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":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"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":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"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":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1606.06650","title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","created":"2016-06-21","cited_by_count":1476},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1711.06396","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","created":"2017-11-17","cited_by_count":1323},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1904.08755","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","created":"2019-04-18","cited_by_count":1208},{"id":"1904.08889","title":"KPConv: Flexible and Deformable Convolution for Point Clouds","created":"2019-04-18","cited_by_count":1205},{"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":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"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":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"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":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1812.04244","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","created":"2018-12-11","cited_by_count":941},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1912.13192","title":"PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection","created":"2019-12-31","cited_by_count":891},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"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":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1801.07791","title":"PointCNN: Convolution On $\\mathcal{X}$-Transformed Points","created":"2018-01-23","cited_by_count":764},{"id":"1711.10275","title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks","created":"2017-11-28","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":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1811.07246","title":"PointConv: Deep Convolutional Networks on 3D Point Clouds","created":"2018-11-17","cited_by_count":657},{"id":"1904.09664","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","created":"2019-04-21","cited_by_count":648},{"id":"1711.08488","title":"Frustum PointNets for 3D Object Detection from RGB-D Data","created":"2017-11-22","cited_by_count":640},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"1911.11236","title":"RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds","created":"2019-11-25","cited_by_count":585},{"id":"1606.06160","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","created":"2016-06-20","cited_by_count":569},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"2007.10985","title":"PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding","created":"2020-07-21","cited_by_count":504},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"1712.01887","title":"Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training","created":"2017-12-05","cited_by_count":478},{"id":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"1711.02281","title":"Non-Autoregressive Neural Machine Translation","created":"2017-11-07","cited_by_count":463},{"id":"1811.08886","title":"HAQ: Hardware-Aware Automated Quantization with Mixed Precision","created":"2018-11-21","cited_by_count":443},{"id":"1703.09039","title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","created":"2017-03-27","cited_by_count":434},{"id":"1310.1531","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","created":"2013-10-06","cited_by_count":424}],"next_cursor":"100"}