{"list":"other","total":74,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"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":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"1610.02242","title":"Temporal Ensembling for Semi-Supervised Learning","created":"2016-10-07","cited_by_count":1057},{"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":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2101.03164","title":"E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials","created":"2021-01-08","cited_by_count":708},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"1904.01169","title":"Res2Net: A New Multi-scale Backbone Architecture","created":"2019-04-02","cited_by_count":470},{"id":"1911.08251","title":"General $E(2)$-Equivariant Steerable CNNs","created":"2019-11-19","cited_by_count":446},{"id":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":445},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"1812.01187","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","created":"2018-12-04","cited_by_count":431},{"id":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"id":"1903.06586","title":"Selective Kernel Networks","created":"2019-03-15","cited_by_count":403},{"id":"1904.11486","title":"Making Convolutional Networks Shift-Invariant Again","created":"2019-04-25","cited_by_count":391},{"id":"1911.11929","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","created":"2019-11-27","cited_by_count":381},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338},{"id":"1612.04642","title":"Harmonic Networks: Deep Translation and Rotation Equivariance","created":"2016-12-14","cited_by_count":295},{"id":"2002.12880","title":"Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data","created":"2020-02-25","cited_by_count":248},{"id":"1411.5908","title":"Understanding image representations by measuring their equivariance and equivalence","created":"2014-11-21","cited_by_count":243},{"id":"1905.00546","title":"Billion-scale semi-supervised learning for image classification","created":"2019-05-02","cited_by_count":232},{"id":"1904.04514","title":"High-Resolution Representations for Labeling Pixels and Regions","created":"2019-04-09","cited_by_count":211},{"id":"2201.09792","title":"Patches Are All You Need?","created":"2022-01-24","cited_by_count":201},{"id":"1805.12177","title":"Why do deep convolutional networks generalize so poorly to small image transformations?","created":"2018-05-30","cited_by_count":198},{"id":"2103.07579","title":"Revisiting ResNets: Improved Training and Scaling Strategies","created":"2021-03-13","cited_by_count":158},{"id":"1907.09595","title":"MixConv: Mixed Depthwise Convolutional Kernels","created":"2019-07-22","cited_by_count":108},{"id":"2012.10885","title":"LieTransformer: Equivariant self-attention for Lie Groups","created":"2020-12-20","cited_by_count":100},{"id":"1612.09346","title":"Rotation equivariant vector field networks","created":"2016-12-29","cited_by_count":99},{"id":"2105.12723","title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding","created":"2021-05-26","cited_by_count":97},{"id":"1806.05594","title":"There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average","created":"2018-06-14","cited_by_count":82},{"id":"1712.02779","title":"Exploring the Landscape of Spatial Robustness","created":"2017-12-07","cited_by_count":81},{"id":"1701.01833","title":"Oriented Response Networks","created":"2017-01-07","cited_by_count":68},{"id":"1907.00837","title":"XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera","created":"2019-07-01","cited_by_count":68},{"id":"1604.06318","title":"TI-POOLING: transformation-invariant pooling for feature learning in Convolutional Neural Networks","created":"2016-04-21","cited_by_count":67},{"id":"1902.04103","title":"Bag of Freebies for Training Object Detection Neural Networks","created":"2019-02-11","cited_by_count":47},{"id":"2007.00992","title":"Rethinking Channel Dimensions for Efficient Model Design","created":"2020-07-02","cited_by_count":41},{"id":"1907.04433","title":"GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing","created":"2019-07-09","cited_by_count":32},{"id":"2106.05121","title":"Grounding inductive biases in natural images:invariance stems from variations in data","created":"2021-06-09","cited_by_count":27},{"id":"2108.03489","title":"Impact of Aliasing on Generalization in Deep Convolutional Networks","created":"2021-08-07","cited_by_count":25},{"id":"2102.07757","title":"How Convolutional Neural Networks Deal with Aliasing","created":"2021-02-15","cited_by_count":10}],"next_cursor":null}