{"list":"other","total":57,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1901.08584","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","created":"2019-01-24","cited_by_count":566},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2006.06882","title":"Rethinking Pre-training and Self-training","created":"2020-06-11","cited_by_count":352},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"1503.00036","title":"Norm-Based Capacity Control in Neural Networks","created":"2015-02-27","cited_by_count":299},{"id":"1804.06516","title":"Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization","created":"2018-04-18","cited_by_count":294},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"2002.09434","title":"Few-Shot Learning via Learning the Representation, Provably","created":"2020-02-21","cited_by_count":214},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"1505.06279","title":"The Benefit of Multitask Representation Learning","created":"2015-05-23","cited_by_count":195},{"id":"2009.07378","title":"BOP Challenge 2020 on 6D Object Localization","created":"2020-09-15","cited_by_count":193},{"id":"1608.08614","title":"What makes ImageNet good for transfer learning?","created":"2016-08-30","cited_by_count":192},{"id":"2006.11650","title":"On the Theory of Transfer Learning: The Importance of Task Diversity","created":"2020-06-20","cited_by_count":186},{"id":"1505.05641","title":"Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views","created":"2015-05-21","cited_by_count":94},{"id":"2102.04074","title":"Learning Curve Theory","created":"2021-02-08","cited_by_count":85},{"id":"2003.14323","title":"How Useful is Self-Supervised Pretraining for Visual Tasks?","created":"2020-03-31","cited_by_count":80},{"id":"1911.01911","title":"BlenderProc","created":"2019-10-25","cited_by_count":77},{"id":"1902.03334","title":"Photorealistic Image Synthesis for Object Instance Detection","created":"2019-02-09","cited_by_count":66},{"id":"2008.09092","title":"Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation","created":"2020-08-20","cited_by_count":58},{"id":"1910.04284","title":"Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin","created":"2019-10-09","cited_by_count":56},{"id":"2004.10802","title":"A Neural Scaling Law from the Dimension of the Data Manifold","created":"2020-04-22","cited_by_count":52},{"id":"1702.07836","title":"Synthesizing Training Data for Object Detection in Indoor Scenes","created":"2017-02-25","cited_by_count":48},{"id":"2106.11344","title":"f-Domain-Adversarial Learning: Theory and Algorithms","created":"2021-06-21","cited_by_count":47},{"id":"2006.12297","title":"Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime","created":"2020-06-22","cited_by_count":35},{"id":"2104.02290","title":"Contrastive Syn-to-Real Generalization","created":"2021-04-06","cited_by_count":32},{"id":"1612.01020","title":"Hypothesis Transfer Learning via Transformation Functions","created":"2016-12-03","cited_by_count":26},{"id":"1905.09870","title":"Gradient Descent can Learn Less Over-parameterized Two-layer Neural Networks on Classification Problems","created":"2019-05-23","cited_by_count":24},{"id":"1603.08152","title":"How useful is photo-realistic rendering for visual learning?","created":"2016-03-26","cited_by_count":22},{"id":"1902.09967","title":"An Annotation Saved is an Annotation Earned: Using Fully Synthetic Training for Object Instance Detection","created":"2019-02-26","cited_by_count":11},{"id":"1807.09834","title":"Applying Domain Randomization to Synthetic Data for Object Category Detection","created":"2018-07-16","cited_by_count":9},{"id":"1806.05438","title":"Stochastic Gradient Descent with Exponential Convergence Rates of Expected Classification Errors","created":"2018-06-14","cited_by_count":6},{"id":"2007.06153","title":"AI Playground: Unreal Engine-based Data Ablation Tool for Deep Learning","created":"2020-07-13","cited_by_count":5}],"next_cursor":null}