{"list":"other","total":56,"rows":[{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"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":"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":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"1905.08094","title":"Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation","created":"2019-05-17","cited_by_count":497},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396},{"id":"1910.01739","title":"Scalable Global Optimization via Local Bayesian Optimization","created":"2019-10-03","cited_by_count":374},{"id":"1703.01041","title":"Large-Scale Evolution of Image Classifiers","created":"2017-03-03","cited_by_count":348},{"id":"1904.01866","title":"A Comprehensive Overhaul of Feature Distillation","created":"2019-04-03","cited_by_count":348},{"id":"1802.04977","title":"Paraphrasing Complex Network: Network Compression via Factor Transfer","created":"2018-02-14","cited_by_count":260},{"id":"1811.03233","title":"Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons","created":"2018-11-08","cited_by_count":238},{"id":"1802.07191","title":"Neural Architecture Search with Bayesian Optimisation and Optimal Transport","created":"2018-02-11","cited_by_count":195},{"id":"1711.00436","title":"Hierarchical Representations for Efficient Architecture Search","created":"2017-11-01","cited_by_count":191},{"id":"2003.11142","title":"BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models","created":"2020-03-24","cited_by_count":188},{"id":"1910.11858","title":"BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search","created":"2019-10-25","cited_by_count":179},{"id":"1610.02915","title":"Deep Pyramidal Residual Networks","created":"2016-10-10","cited_by_count":163},{"id":"2104.10201","title":"Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020","created":"2021-04-20","cited_by_count":148},{"id":"1911.12207","title":"Orthogonal Convolutional Neural Networks","created":"2019-11-27","cited_by_count":123},{"id":"1902.08142","title":"Evaluating the Search Phase of Neural Architecture Search","created":"2019-02-21","cited_by_count":120},{"id":"2007.00708","title":"Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search","created":"2020-07-01","cited_by_count":89},{"id":"1803.00443","title":"Knowledge Transfer with Jacobian Matching","created":"2018-03-01","cited_by_count":76},{"id":"2011.09011","title":"AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling","created":"2020-11-18","cited_by_count":66},{"id":"1810.09102","title":"Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?","created":"2018-10-22","cited_by_count":62},{"id":"1703.01827","title":"All You Need is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks with Orthonormality and Modulation","created":"2017-03-06","cited_by_count":58},{"id":"2006.06863","title":"Few-shot Neural Architecture Search","created":"2020-06-11","cited_by_count":50},{"id":"2006.16992","title":"Deep Isometric Learning for Visual Recognition","created":"2020-06-30","cited_by_count":39},{"id":"2012.08859","title":"Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces","created":"2020-12-16","cited_by_count":32},{"id":"2003.02838","title":"Accelerator-aware Neural Network Design using AutoML","created":"2020-03-05","cited_by_count":30},{"id":"2101.06808","title":"TREGO: a Trust-Region Framework for Efficient Global Optimization","created":"2021-01-18","cited_by_count":29},{"id":"1911.09074","title":"Search to Distill: Pearls are Everywhere but not the Eyes","created":"2019-11-20","cited_by_count":26},{"id":"2110.04035","title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","created":"2021-10-08","cited_by_count":23},{"id":"2102.05610","title":"Searching for Fast Model Families on Datacenter Accelerators","created":"2021-02-10","cited_by_count":22},{"id":"2106.11890","title":"Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization","created":"2021-06-22","cited_by_count":15},{"id":"1911.13019","title":"Towards Oracle Knowledge Distillation with Neural Architecture Search","created":"2019-11-29","cited_by_count":13},{"id":"1908.06022","title":"SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search","created":"2019-08-16","cited_by_count":6}],"next_cursor":null}