{"list":"other","total":81,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"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":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1902.06720","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","created":"2019-02-18","cited_by_count":738},{"id":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1707.08819","title":"A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets","created":"2017-07-27","cited_by_count":377},{"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":"1812.09926","title":"SNAS: Stochastic Neural Architecture Search","created":"2018-12-24","cited_by_count":289},{"id":"1907.05737","title":"PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search","created":"2019-07-12","cited_by_count":265},{"id":"1910.04465","title":"Searching for A Robust Neural Architecture in Four GPU Hours","created":"2019-10-10","cited_by_count":260},{"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":"1911.13299","title":"What's Hidden in a Randomly Weighted Neural Network?","created":"2019-11-29","cited_by_count":237},{"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":"1708.05344","title":"SMASH: One-Shot Model Architecture Search through HyperNetworks","created":"2017-08-17","cited_by_count":202},{"id":"2101.08134","title":"Zero-Cost Proxies for Lightweight NAS","created":"2021-01-20","cited_by_count":199},{"id":"1802.07191","title":"Neural Architecture Search with Bayesian Optimisation and Optimal Transport","created":"2018-02-11","cited_by_count":195},{"id":"2003.11142","title":"BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models","created":"2020-03-24","cited_by_count":188},{"id":"1909.09656","title":"Understanding and Robustifying Differentiable Architecture Search","created":"2019-09-20","cited_by_count":178},{"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":"1901.09021","title":"Complexity of Linear Regions in Deep Networks","created":"2019-01-25","cited_by_count":167},{"id":"1610.02915","title":"Deep Pyramidal Residual Networks","created":"2016-10-10","cited_by_count":163},{"id":"1711.02114","title":"Bounding and Counting Linear Regions of Deep Neural Networks","created":"2017-11-06","cited_by_count":161},{"id":"1906.00904","title":"Deep ReLU Networks Have Surprisingly Few Activation Patterns","created":"2019-06-03","cited_by_count":161},{"id":"1902.08142","title":"Evaluating the Search Phase of Neural Architecture Search","created":"2019-02-21","cited_by_count":120},{"id":"1909.05989","title":"Finite Depth and Width Corrections to the Neural Tangent Kernel","created":"2019-09-13","cited_by_count":115},{"id":"2002.11448","title":"Predicting Neural Network Accuracy from Weights","created":"2020-02-26","cited_by_count":110},{"id":"1909.06035","title":"DARTS+: Improved Differentiable Architecture Search with Early Stopping","created":"2019-09-13","cited_by_count":105},{"id":"1902.06853","title":"On the Impact of the Activation Function on Deep Neural Networks Training","created":"2019-02-19","cited_by_count":102},{"id":"2002.05283","title":"Stabilizing Differentiable Architecture Search via Perturbation-based Regularization","created":"2020-02-12","cited_by_count":102},{"id":"1509.05009","title":"On the Expressive Power of Deep Learning: A Tensor Analysis","created":"2015-09-16","cited_by_count":97},{"id":"1809.04184","title":"Searching for Efficient Multi-Scale Architectures for Dense Image Prediction","created":"2018-09-11","cited_by_count":96},{"id":"1908.03835","title":"AutoGAN: Neural Architecture Search for Generative Adversarial Networks","created":"2019-08-11","cited_by_count":94},{"id":"1912.10917","title":"FasterSeg: Searching for Faster Real-time Semantic Segmentation","created":"2019-12-23","cited_by_count":73},{"id":"2006.10355","title":"DrNAS: Dirichlet Neural Architecture Search","created":"2020-06-18","cited_by_count":73},{"id":"1906.04358","title":"Weight Agnostic Neural Networks","created":"2019-06-11","cited_by_count":71},{"id":"1912.00195","title":"SGAS: Sequential Greedy Architecture Search","created":"2019-11-30","cited_by_count":69},{"id":"1905.04919","title":"BayesNAS: A Bayesian Approach for Neural Architecture Search","created":"2019-05-13","cited_by_count":68},{"id":"1905.13214","title":"On Network Design Spaces for Visual Recognition","created":"2019-05-30","cited_by_count":68},{"id":"2007.06559","title":"Graph Structure of Neural Networks","created":"2020-07-13","cited_by_count":68},{"id":"2001.01233","title":"EcoNAS: Finding Proxies for Economical Neural Architecture Search","created":"2020-01-05","cited_by_count":61},{"id":"1810.07481","title":"Provable Robustness of ReLU networks via Maximization of Linear Regions","created":"2018-10-17","cited_by_count":51},{"id":"2006.06863","title":"Few-shot Neural Architecture Search","created":"2020-06-11","cited_by_count":50},{"id":"2006.08198","title":"AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks","created":"2020-06-15","cited_by_count":50},{"id":"2006.00978","title":"On the Number of Linear Regions of Convolutional Neural Networks","created":"2020-06-01","cited_by_count":49},{"id":"1909.09569","title":"Understanding Architectures Learnt by Cell-based Neural Architecture Search","created":"2019-09-20","cited_by_count":48},{"id":"1504.08291","title":"Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?","created":"2015-04-30","cited_by_count":41},{"id":"2101.11834","title":"Neural Architecture Search with Random Labels","created":"2021-01-28","cited_by_count":33},{"id":"1905.13577","title":"Efficient Neural Architecture Search via Proximal Iterations","created":"2019-05-30","cited_by_count":31},{"id":"2102.10490","title":"Stronger NAS with Weaker Predictors","created":"2021-02-21","cited_by_count":28},{"id":"2011.06006","title":"Towards NNGP-guided Neural Architecture Search","created":"2020-11-11","cited_by_count":24},{"id":"2102.07108","title":"CATE: Computation-aware Neural Architecture Encoding with Transformers","created":"2021-02-14","cited_by_count":21},{"id":"2003.04276","title":"How to Train Your Super-Net: An Analysis of Training Heuristics in Weight-Sharing NAS","created":"2020-03-09","cited_by_count":17},{"id":"1912.13053","title":"Disentangling Trainability and Generalization in Deep Neural Networks","created":"2019-12-30","cited_by_count":16},{"id":"2108.01899","title":"Generic Neural Architecture Search via Regression","created":"2021-08-04","cited_by_count":14},{"id":"2008.02953","title":"Neural Complexity Measures","created":"2020-08-07","cited_by_count":11},{"id":"2011.10949","title":"FP-NAS: Fast Probabilistic Neural Architecture Search","created":"2020-11-22","cited_by_count":11},{"id":"2005.14446","title":"HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens","created":"2020-05-29","cited_by_count":8},{"id":"2009.01272","title":"Understanding the wiring evolution in differentiable neural architecture search","created":"2020-09-02","cited_by_count":3},{"id":"2108.08128","title":"Single-DARTS: Towards Stable Architecture Search","created":"2021-08-18","cited_by_count":3},{"id":"1910.00780","title":"How does topology influence gradient propagation and model performance of deep networks with DenseNet-type skip connections?","created":"2019-10-02","cited_by_count":1}],"next_cursor":null}