{"list":"other","total":55,"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":"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"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":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"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":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"1701.04128","title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","created":"2017-01-15","cited_by_count":553},{"id":"1707.06342","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","created":"2017-07-20","cited_by_count":442},{"id":"1911.11907","title":"GhostNet: More Features from Cheap Operations","created":"2019-11-27","cited_by_count":410},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"1904.12760","title":"Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation","created":"2019-04-29","cited_by_count":230},{"id":"1302.4389","title":"Maxout Networks","created":"2013-02-18","cited_by_count":187},{"id":"1707.01213","title":"Data-Driven Sparse Structure Selection for Deep Neural Networks","created":"2017-07-05","cited_by_count":181},{"id":"2103.07579","title":"Revisiting ResNets: Improved Training and Scaling Strategies","created":"2021-03-13","cited_by_count":158},{"id":"1911.12126","title":"Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search","created":"2019-11-27","cited_by_count":131},{"id":"1909.06035","title":"DARTS+: Improved Differentiable Architecture Search with Early Stopping","created":"2019-09-13","cited_by_count":105},{"id":"1711.08141","title":"Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions","created":"2017-11-22","cited_by_count":93},{"id":"1710.04773","title":"Residual Connections Encourage Iterative Inference","created":"2017-10-13","cited_by_count":77},{"id":"1810.09957","title":"NSML: Meet the MLaaS platform with a real-world case study","created":"2018-10-08","cited_by_count":70},{"id":"1612.07771","title":"Highway and Residual Networks learn Unrolled Iterative Estimation","created":"2016-12-22","cited_by_count":52},{"id":"2007.00992","title":"Rethinking Channel Dimensions for Efficient Model Design","created":"2020-07-02","cited_by_count":41},{"id":"1903.05285","title":"All You Need is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classification","created":"2019-03-13","cited_by_count":38},{"id":"2006.09791","title":"Optimizing Grouped Convolutions on Edge Devices","created":"2020-06-17","cited_by_count":12},{"id":"2003.07469","title":"SlimConv: Reducing Channel Redundancy in Convolutional Neural Networks by Weights Flipping","created":"2020-03-16","cited_by_count":11},{"id":"1705.07038","title":"The Landscape of Deep Learning Algorithms","created":"2017-05-19","cited_by_count":1}],"next_cursor":null}