{"list":"other","total":75,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1511.07247","title":"NetVLAD: CNN architecture for weakly supervised place recognition","created":"2015-11-23","cited_by_count":941},{"id":"1710.11063","title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","created":"2017-10-30","cited_by_count":939},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1910.03151","title":"ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks","created":"2019-10-08","cited_by_count":575},{"id":"1904.11486","title":"Making Convolutional Networks Shift-Invariant Again","created":"2019-04-25","cited_by_count":391},{"id":"1704.06904","title":"Residual Attention Network for Image Classification","created":"2017-04-23","cited_by_count":386},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339},{"id":"1904.03582","title":"Multi-Label Image Recognition with Graph Convolutional Networks","created":"2019-04-07","cited_by_count":322},{"id":"1504.07889","title":"Bilinear CNNs for Fine-grained Visual Recognition","created":"2015-04-29","cited_by_count":228},{"id":"1802.08122","title":"Harmonious Attention Network for Person Re-Identification","created":"2018-02-22","cited_by_count":211},{"id":"2107.10834","title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","created":"2021-07-22","cited_by_count":128},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126},{"id":"2106.03650","title":"Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer","created":"2021-06-07","cited_by_count":115},{"id":"2106.12368","title":"Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition","created":"2021-06-23","cited_by_count":103},{"id":"1511.06062","title":"Compact Bilinear Pooling","created":"2015-11-19","cited_by_count":97},{"id":"1702.05891","title":"Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification","created":"2017-02-20","cited_by_count":85},{"id":"2106.07477","title":"S$^2$-MLP: Spatial-Shift MLP Architecture for Vision","created":"2021-06-14","cited_by_count":83},{"id":"1506.03767","title":"Spectral Representations for Convolutional Neural Networks","created":"2015-06-11","cited_by_count":81},{"id":"1912.07872","title":"Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification","created":"2019-12-17","cited_by_count":79},{"id":"1811.12006","title":"Global Second-order Pooling Convolutional Networks","created":"2018-11-29","cited_by_count":66},{"id":"1712.01034","title":"Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization","created":"2017-12-04","cited_by_count":65},{"id":"2105.02723","title":"Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet","created":"2021-05-06","cited_by_count":61},{"id":"2108.02456","title":"Residual Attention: A Simple but Effective Method for Multi-Label Recognition","created":"2021-08-05","cited_by_count":52},{"id":"2007.01755","title":"Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition","created":"2020-07-03","cited_by_count":50},{"id":"2007.11823","title":"WeightNet: Revisiting the Design Space of Weight Networks","created":"2020-07-23","cited_by_count":50},{"id":"1301.3557","title":"Stochastic Pooling for Regularization of Deep Convolutional Neural Networks","created":"2013-01-16","cited_by_count":48},{"id":"1904.06836","title":"Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization","created":"2019-04-15","cited_by_count":42},{"id":"1509.08985","title":"Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree","created":"2015-09-30","cited_by_count":36},{"id":"1908.04156","title":"LIP: Local Importance-based Pooling","created":"2019-08-12","cited_by_count":30},{"id":"1804.04076","title":"Detail-Preserving Pooling in Deep Networks","created":"2018-04-11","cited_by_count":26},{"id":"1910.05577","title":"Context-Gated Convolution","created":"2019-10-12","cited_by_count":23},{"id":"1611.05138","title":"S3Pool: Pooling with Stochastic Spatial Sampling","created":"2016-11-16","cited_by_count":17},{"id":"2108.07884","title":"Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs","created":"2021-08-17","cited_by_count":12},{"id":"2104.00996","title":"LiftPool: Bidirectional ConvNet Pooling","created":"2021-04-02","cited_by_count":11},{"id":"2211.04625","title":"Soft Augmentation for Image Classification","created":"2022-11-09","cited_by_count":11},{"id":"1411.7466","title":"The Treasure beneath Convolutional Layers: Cross-convolutional-layer Pooling for Image Classification","created":"2014-11-27","cited_by_count":9},{"id":"2003.11241","title":"What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective","created":"2020-03-25","cited_by_count":8},{"id":"2106.11596","title":"Multi-layered Semantic Representation Network for Multi-label Image Classification","created":"2021-06-22","cited_by_count":6},{"id":"2004.07570","title":"Spatially Attentive Output Layer for Image Classification","created":"2020-04-16","cited_by_count":5},{"id":"2104.10935","title":"SoT: Delving Deeper into Classification Head for Transformer","created":"2021-04-22","cited_by_count":5},{"id":"1802.07303","title":"MoNet: Moments Embedding Network","created":"2018-02-20","cited_by_count":4},{"id":"1608.00182","title":"Deep FisherNet for Object Classification","created":"2016-07-31","cited_by_count":1}],"next_cursor":null}