{"list":"other","total":68,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"1807.01774","title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","created":"2018-07-04","cited_by_count":470},{"id":"2001.00326","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","created":"2020-01-02","cited_by_count":416},{"id":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"id":"1402.1869","title":"On the Number of Linear Regions of Deep Neural Networks","created":"2014-02-08","cited_by_count":381},{"id":"1805.11604","title":"How Does Batch Normalization Help Optimization?","created":"2018-05-29","cited_by_count":357},{"id":"1902.09635","title":"NAS-Bench-101: Towards Reproducible Neural Architecture Search","created":"2019-02-25","cited_by_count":344},{"id":"1606.05336","title":"On the Expressive Power of Deep Neural Networks","created":"2016-06-16","cited_by_count":306},{"id":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","created":"2015-02-19","cited_by_count":284},{"id":"1705.08741","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","created":"2017-05-24","cited_by_count":279},{"id":"1907.05737","title":"PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search","created":"2019-07-12","cited_by_count":265},{"id":"1606.05340","title":"Exponential expressivity in deep neural networks through transient chaos","created":"2016-06-16","cited_by_count":261},{"id":"1902.07638","title":"Random Search and Reproducibility for Neural Architecture Search","created":"2019-02-20","cited_by_count":254},{"id":"2006.04647","title":"Neural Architecture Search without Training","created":"2020-06-08","cited_by_count":244},{"id":"2101.08134","title":"Zero-Cost Proxies for Lightweight NAS","created":"2021-01-20","cited_by_count":199},{"id":"1910.11858","title":"BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search","created":"2019-10-25","cited_by_count":179},{"id":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169},{"id":"1808.07233","title":"Neural Architecture Optimization","created":"2018-08-22","cited_by_count":167},{"id":"1806.02375","title":"Understanding Batch Normalization","created":"2018-06-01","cited_by_count":159},{"id":"1911.12126","title":"Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search","created":"2019-11-27","cited_by_count":131},{"id":"1907.01845","title":"FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search","created":"2019-07-03","cited_by_count":130},{"id":"1912.00848","title":"Neural Predictor for Neural Architecture Search","created":"2019-12-02","cited_by_count":118},{"id":"1909.06035","title":"DARTS+: Improved Differentiable Architecture Search with Early Stopping","created":"2019-09-13","cited_by_count":105},{"id":"2003.00152","title":"Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs","created":"2020-02-29","cited_by_count":104},{"id":"2104.01177","title":"How Powerful are Performance Predictors in Neural Architecture Search?","created":"2021-04-02","cited_by_count":90},{"id":"1903.10979","title":"DetNAS: Backbone Search for Object Detection","created":"2019-03-26","cited_by_count":81},{"id":"2009.01027","title":"DARTS-: Robustly Stepping out of Performance Collapse Without Indicators","created":"2020-09-02","cited_by_count":81},{"id":"1911.00809","title":"Enhanced Convolutional Neural Tangent Kernels","created":"2019-11-03","cited_by_count":76},{"id":"1802.06455","title":"Bayesian Uncertainty Estimation for Batch Normalized Deep Networks","created":"2018-02-18","cited_by_count":70},{"id":"1910.05733","title":"One-Shot Neural Architecture Search via Self-Evaluated Template Network","created":"2019-10-13","cited_by_count":69},{"id":"2003.11236","title":"GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet","created":"2020-03-25","cited_by_count":69},{"id":"1606.04820","title":"Understanding Probabilistic Sparse Gaussian Process Approximations","created":"2016-06-15","cited_by_count":68},{"id":"1902.08129","title":"A Mean Field Theory of Batch Normalization","created":"2019-02-21","cited_by_count":58},{"id":"1906.04423","title":"NAS-FCOS: Fast Neural Architecture Search for Object Detection","created":"2019-06-11","cited_by_count":53},{"id":"2002.10389","title":"Semi-Supervised Neural Architecture Search","created":"2020-02-24","cited_by_count":46},{"id":"2105.07576","title":"Rethinking \"Batch\" in BatchNorm","created":"2021-05-17","cited_by_count":45},{"id":"1903.11059","title":"AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search","created":"2019-03-26","cited_by_count":33},{"id":"2101.11834","title":"Neural Architecture Search with Random Labels","created":"2021-01-28","cited_by_count":33},{"id":"2004.13431","title":"Angle-based Search Space Shrinking for Neural Architecture Search","created":"2020-04-28","cited_by_count":32},{"id":"2106.03970","title":"Batch Normalization Orthogonalizes Representations in Deep Random Networks","created":"2021-06-07","cited_by_count":29},{"id":"2108.07375","title":"BN-NAS: Neural Architecture Search with Batch Normalization","created":"2021-08-16","cited_by_count":21},{"id":"2102.05543","title":"Partial transfusion: on the expressive influence of trainable batch norm parameters for transfer learning","created":"2021-02-10","cited_by_count":15},{"id":"1811.09828","title":"Evolutionary-Neural Hybrid Agents for Architecture Search","created":"2018-11-24","cited_by_count":11},{"id":"1907.05715","title":"Order and Chaos: NTK views on DNN Normalization, Checkerboard and Boundary Artifacts","created":"2019-07-11","cited_by_count":7},{"id":"2007.04785","title":"Accuracy Prediction with Non-neural Model for Neural Architecture Search","created":"2020-07-09","cited_by_count":5},{"id":"2107.03719","title":"Bag of Tricks for Neural Architecture Search","created":"2021-07-08","cited_by_count":4}],"next_cursor":null}