{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"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":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"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":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"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":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"2009.14119","title":"Asymmetric Loss For Multi-Label Classification","created":"2020-09-29","cited_by_count":381},{"id":"1904.01866","title":"A Comprehensive Overhaul of Feature Distillation","created":"2019-04-03","cited_by_count":348},{"id":"2006.09994","title":"Noise or Signal: The Role of Image Backgrounds in Object Recognition","created":"2020-06-17","cited_by_count":343},{"id":"2006.07159","title":"Are we done with ImageNet?","created":"2020-06-12","cited_by_count":333},{"id":"1904.03582","title":"Multi-Label Image Recognition with Graph Convolutional Networks","created":"2019-04-07","cited_by_count":322},{"id":"1810.12890","title":"DropBlock: A regularization method for convolutional networks","created":"2018-10-30","cited_by_count":262},{"id":"1811.03233","title":"Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons","created":"2018-11-08","cited_by_count":238},{"id":"1905.00546","title":"Billion-scale semi-supervised learning for image classification","created":"2019-05-02","cited_by_count":232},{"id":"1906.06423","title":"Fixing the train-test resolution discrepancy","created":"2019-06-14","cited_by_count":209},{"id":"1806.04606","title":"Knowledge Distillation by On-the-Fly Native Ensemble","created":"2018-06-12","cited_by_count":186},{"id":"1610.02915","title":"Deep Pyramidal Residual Networks","created":"2016-10-10","cited_by_count":163},{"id":"1405.3531","title":"Return of the Devil in the Details: Delving Deep into Convolutional Nets","created":"2014-05-14","cited_by_count":122},{"id":"1812.00123","title":"Snapshot Distillation: Teacher-Student Optimization in One Generation","created":"2018-12-01","cited_by_count":99},{"id":"2005.11295","title":"From ImageNet to Image Classification: Contextualizing Progress on Benchmarks","created":"2020-05-22","cited_by_count":90},{"id":"1711.02816","title":"Multi-label Image Recognition by Recurrently Discovering Attentional Regions","created":"2017-11-08","cited_by_count":83},{"id":"1912.07872","title":"Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification","created":"2019-12-17","cited_by_count":79},{"id":"1810.09957","title":"NSML: Meet the MLaaS platform with a real-world case study","created":"2018-10-08","cited_by_count":70},{"id":"1812.02425","title":"MEAL: Multi-Model Ensemble via Adversarial Learning","created":"2018-12-06","cited_by_count":52},{"id":"2006.08217","title":"AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights","created":"2020-06-15","cited_by_count":10}],"next_cursor":null}