{"list":"other","total":99,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"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":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"2002.08791","title":"Bayesian Deep Learning and a Probabilistic Perspective of Generalization","created":"2020-02-20","cited_by_count":480},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"id":"1904.01685","title":"Measuring Calibration in Deep Learning","created":"2019-04-02","cited_by_count":446},{"id":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","created":"2019-12-05","cited_by_count":443},{"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":"1704.00109","title":"Snapshot Ensembles: Train 1, get M for free","created":"2017-04-01","cited_by_count":350},{"id":"1911.09785","title":"ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring","created":"2019-11-21","cited_by_count":349},{"id":"1810.12890","title":"DropBlock: A regularization method for convolutional networks","created":"2018-10-30","cited_by_count":262},{"id":"2009.06962","title":"Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup","created":"2020-09-15","cited_by_count":261},{"id":"1901.08846","title":"Improving Adversarial Robustness via Promoting Ensemble Diversity","created":"2019-01-25","cited_by_count":213},{"id":"2002.06470","title":"Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning","created":"2020-02-15","cited_by_count":210},{"id":"2007.07936","title":"ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning","created":"2020-07-15","cited_by_count":209},{"id":"1902.03932","title":"Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning","created":"2019-02-11","cited_by_count":203},{"id":"2002.00585","title":"Proving the Lottery Ticket Hypothesis: Pruning is All You Need","created":"2020-02-03","cited_by_count":201},{"id":"2010.04819","title":"How Does Mixup Help With Robustness and Generalization?","created":"2020-10-09","cited_by_count":193},{"id":"2003.07329","title":"Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning","created":"2020-03-16","cited_by_count":190},{"id":"1806.04606","title":"Knowledge Distillation by On-the-Fly Native Ensemble","created":"2018-06-12","cited_by_count":186},{"id":"1906.01620","title":"Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision","created":"2019-06-04","cited_by_count":182},{"id":"2010.06610","title":"Training independent subnetworks for robust prediction","created":"2020-10-13","cited_by_count":177},{"id":"2005.07186","title":"Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors","created":"2020-05-14","cited_by_count":171},{"id":"1809.02499","title":"MixUp as Locally Linear Out-Of-Manifold Regularization","created":"2018-09-07","cited_by_count":158},{"id":"2006.13570","title":"Hyperparameter Ensembles for Robustness and Uncertainty Quantification","created":"2020-06-24","cited_by_count":150},{"id":"2006.01791","title":"SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization","created":"2020-06-02","cited_by_count":149},{"id":"1511.06314","title":"Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks","created":"2015-11-19","cited_by_count":139},{"id":"1705.06676","title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering","created":"2017-05-18","cited_by_count":137},{"id":"1912.00350","title":"Online Knowledge Distillation with Diverse Peers","created":"2019-12-01","cited_by_count":128},{"id":"2102.03065","title":"Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity","created":"2021-02-05","cited_by_count":128},{"id":"1801.02929","title":"Data Augmentation by Pairing Samples for Images Classification","created":"2018-01-09","cited_by_count":96},{"id":"2007.05864","title":"Bayesian Deep Ensembles via the Neural Tangent Kernel","created":"2020-07-11","cited_by_count":90},{"id":"1811.09030","title":"Data Augmentation using Random Image Cropping and Patching for Deep CNNs","created":"2018-11-22","cited_by_count":88},{"id":"2012.08334","title":"Masksembles for Uncertainty Estimation","created":"2020-12-15","cited_by_count":88},{"id":"2006.06049","title":"On Mixup Regularization","created":"2020-06-10","cited_by_count":83},{"id":"2006.07990","title":"Optimal Lottery Tickets via SubsetSum: Logarithmic Over-Parameterization is Sufficient","created":"2020-06-14","cited_by_count":81},{"id":"1910.11385","title":"Calibration tests in multi-class classification: A unifying framework","created":"2019-10-24","cited_by_count":79},{"id":"2002.11102","title":"On Feature Normalization and Data Augmentation","created":"2020-02-25","cited_by_count":71},{"id":"1805.11761","title":"Collaborative Learning for Deep Neural Networks","created":"2018-05-30","cited_by_count":69},{"id":"2001.10995","title":"The Case for Bayesian Deep Learning","created":"2020-01-29","cited_by_count":69},{"id":"2012.11101","title":"ResizeMix: Mixing Data with Preserved Object Information and True Labels","created":"2020-12-21","cited_by_count":69},{"id":"1902.09487","title":"MUREL: Multimodal Relational Reasoning for Visual Question Answering","created":"2019-02-25","cited_by_count":68},{"id":"1810.08591","title":"A Modern Take on the Bias-Variance Tradeoff in Neural Networks","created":"2018-10-19","cited_by_count":65},{"id":"2102.06289","title":"When and How Mixup Improves Calibration","created":"2021-02-11","cited_by_count":60},{"id":"2003.05034","title":"SuperMix: Supervising the Mixing Data Augmentation","created":"2020-03-10","cited_by_count":58},{"id":"1711.10282","title":"Learning from Between-class Examples for Deep Sound Recognition","created":"2017-11-28","cited_by_count":54},{"id":"1711.10284","title":"Between-class Learning for Image Classification","created":"2017-11-28","cited_by_count":50},{"id":"1611.06440","title":"Pruning Convolutional Neural Networks for Resource Efficient Inference","created":"2016-11-19","cited_by_count":48},{"id":"2101.05544","title":"DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation","created":"2021-01-14","cited_by_count":48},{"id":"2002.08973","title":"Affinity and Diversity: Quantifying Mechanisms of Data Augmentation","created":"2020-02-20","cited_by_count":45},{"id":"2010.09875","title":"Combining Ensembles and Data Augmentation can Harm your Calibration","created":"2020-10-19","cited_by_count":44},{"id":"1805.11272","title":"Improved Mixed-Example Data Augmentation","created":"2018-05-29","cited_by_count":42},{"id":"1811.02545","title":"Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and Beyond","created":"2018-11-06","cited_by_count":36},{"id":"1912.06844","title":"Regularizing Deep Multi-Task Networks using Orthogonal Gradients","created":"2019-12-14","cited_by_count":36},{"id":"2003.12022","title":"Milking CowMask for Semi-Supervised Image Classification","created":"2020-03-26","cited_by_count":35},{"id":"1909.09148","title":"Data Augmentation Revisited: Rethinking the Distribution Gap between Clean and Augmented Data","created":"2019-09-19","cited_by_count":33},{"id":"2001.04694","title":"Hydra: Preserving Ensemble Diversity for Model Distillation","created":"2020-01-14","cited_by_count":31},{"id":"2007.08483","title":"On Power Laws in Deep Ensembles","created":"2020-07-16","cited_by_count":26},{"id":"1810.11530","title":"Automatic differentiation in ML: Where we are and where we should be going","created":"2018-10-26","cited_by_count":20},{"id":"2010.08887","title":"i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning","created":"2020-10-17","cited_by_count":19},{"id":"2006.07989","title":"GradAug: A New Regularization Method for Deep Neural Networks","created":"2020-06-14","cited_by_count":18},{"id":"2002.11531","title":"A general framework for ensemble distribution distillation","created":"2020-02-26","cited_by_count":16},{"id":"1809.04270","title":"MotherNets: Rapid Deep Ensemble Learning","created":"2018-09-12","cited_by_count":14},{"id":"1509.08967","title":"Very Deep Multilingual Convolutional Neural Networks for LVCSR","created":"2015-09-29","cited_by_count":11},{"id":"2006.07877","title":"FenceMask: A Data Augmentation Approach for Pre-extracted Image Features","created":"2020-06-14","cited_by_count":10},{"id":"2005.07292","title":"Deep Ensembles on a Fixed Memory Budget: One Wide Network or Several Thinner Ones?","created":"2020-05-14","cited_by_count":6},{"id":"2001.03955","title":"Aggregated Learning: A Vector-Quantization Approach to Learning Neural Network Classifiers","created":"2020-01-12","cited_by_count":5},{"id":"1904.04466","title":"Intra-Ensemble in Neural Networks","created":"2019-04-09","cited_by_count":2},{"id":"2003.02065","title":"Mixup Regularization for Region Proposal based Object Detectors","created":"2020-03-04","cited_by_count":2},{"id":"2011.12618","title":"StackMix: A complementary Mix algorithm","created":"2020-11-25","cited_by_count":1}],"next_cursor":null}