{"list":"other","total":97,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"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":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"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":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1804.06872","title":"Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels","created":"2018-04-18","cited_by_count":1059},{"id":"1610.02242","title":"Temporal Ensembling for Semi-Supervised Learning","created":"2016-10-07","cited_by_count":1057},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"id":"2002.07394","title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","created":"2020-02-18","cited_by_count":692},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"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":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"2002.11569","title":"Overfitting in adversarially robust deep learning","created":"2020-02-26","cited_by_count":506},{"id":"1703.01780","title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","created":"2017-03-06","cited_by_count":472},{"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":"1807.00263","title":"Accurate Uncertainties for Deep Learning Using Calibrated Regression","created":"2018-07-01","cited_by_count":422},{"id":"1905.13736","title":"Unlabeled Data Improves Adversarial Robustness","created":"2019-05-31","cited_by_count":416},{"id":"2007.00151","title":"Early-Learning Regularization Prevents Memorization of Noisy Labels","created":"2020-06-30","cited_by_count":416},{"id":"1911.00068","title":"Confident Learning: Estimating Uncertainty in Dataset Labels","created":"2019-10-31","cited_by_count":413},{"id":"1711.09325","title":"Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples","created":"2017-11-26","cited_by_count":389},{"id":"1901.09960","title":"Using Pre-Training Can Improve Model Robustness and Uncertainty","created":"2019-01-28","cited_by_count":373},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"1910.12656","title":"Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration","created":"2019-10-28","cited_by_count":364},{"id":"2002.09437","title":"Calibrating Deep Neural Networks using Focal Loss","created":"2020-02-21","cited_by_count":357},{"id":"1704.00109","title":"Snapshot Ensembles: Train 1, get M for free","created":"2017-04-01","cited_by_count":350},{"id":"1901.09192","title":"SelectiveNet: A Deep Neural Network with an Integrated Reject Option","created":"2019-01-26","cited_by_count":350},{"id":"2004.12993","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","created":"2020-04-27","cited_by_count":332},{"id":"1909.10155","title":"Verified Uncertainty Calibration","created":"2019-09-23","cited_by_count":309},{"id":"1905.11001","title":"On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks","created":"2019-05-27","cited_by_count":305},{"id":"2101.06329","title":"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning","created":"2021-01-15","cited_by_count":301},{"id":"1807.07356","title":"Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks","created":"2018-07-19","cited_by_count":280},{"id":"2010.03593","title":"Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples","created":"2020-10-07","cited_by_count":278},{"id":"2001.10528","title":"Identifying Mislabeled Data using the Area Under the Margin Ranking","created":"2020-01-28","cited_by_count":261},{"id":"1802.04865","title":"Learning Confidence for Out-of-Distribution Detection in Neural Networks","created":"2018-02-13","cited_by_count":245},{"id":"1412.4864","title":"Learning with Pseudo-Ensembles","created":"2014-12-16","cited_by_count":241},{"id":"2110.09468","title":"Improving Robustness using Generated Data","created":"2021-10-18","cited_by_count":234},{"id":"2004.02178","title":"FastBERT: a Self-distilling BERT with Adaptive Inference Time","created":"2020-04-05","cited_by_count":226},{"id":"1805.11783","title":"To Trust Or Not To Trust A Classifier","created":"2018-05-30","cited_by_count":207},{"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":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190},{"id":"1910.04851","title":"Addressing Failure Prediction by Learning Model Confidence","created":"2019-10-01","cited_by_count":186},{"id":"1902.06977","title":"Evaluating model calibration in classification","created":"2019-02-19","cited_by_count":168},{"id":"1905.13725","title":"Are Labels Required for Improving Adversarial Robustness?","created":"2019-05-31","cited_by_count":163},{"id":"2006.13570","title":"Hyperparameter Ensembles for Robustness and Uncertainty Quantification","created":"2020-06-24","cited_by_count":150},{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141},{"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":"2004.07453","title":"The Right Tool for the Job: Matching Model and Instance Complexities","created":"2020-04-16","cited_by_count":126},{"id":"1805.08206","title":"Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers","created":"2018-05-21","cited_by_count":113},{"id":"2007.01458","title":"Confidence-Aware Learning for Deep Neural Networks","created":"2020-07-03","cited_by_count":113},{"id":"2104.09425","title":"Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?","created":"2021-04-19","cited_by_count":113},{"id":"2106.15853","title":"Understanding and Improving Early Stopping for Learning with Noisy Labels","created":"2021-06-30","cited_by_count":113},{"id":"2006.12000","title":"Self-Knowledge Distillation with Progressive Refinement of Targets","created":"2020-06-22","cited_by_count":107},{"id":"2008.11600","title":"Estimating Example Difficulty Using Variance of Gradients","created":"2020-08-26","cited_by_count":97},{"id":"1807.01771","title":"Direct Uncertainty Prediction for Medical Second Opinions","created":"2018-07-04","cited_by_count":61},{"id":"1804.00382","title":"Attention-based Ensemble for Deep Metric Learning","created":"2018-04-02","cited_by_count":56},{"id":"1905.10854","title":"Let's Agree to Agree: Neural Networks Share Classification Order on Real Datasets","created":"2019-05-26","cited_by_count":56},{"id":"2010.11422","title":"Learning Loss for Test-Time Augmentation","created":"2020-10-22","cited_by_count":56},{"id":"2008.08030","title":"Gradients as a Measure of Uncertainty in Neural Networks","created":"2020-08-18","cited_by_count":55},{"id":"2010.09875","title":"Combining Ensembles and Data Augmentation can Harm your Calibration","created":"2020-10-19","cited_by_count":44},{"id":"1805.08440","title":"Classification Uncertainty of Deep Neural Networks Based on Gradient Information","created":"2018-05-22","cited_by_count":43},{"id":"1910.13427","title":"Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications","created":"2019-10-29","cited_by_count":43},{"id":"2206.02757","title":"Robust Calibration with Multi-domain Temperature Scaling","created":"2022-06-06","cited_by_count":39},{"id":"2003.02037","title":"Uncertainty Estimation Using a Single Deep Deterministic Neural Network","created":"2020-03-04","cited_by_count":37},{"id":"1810.07884","title":"Automatic Brain Tumor Segmentation using Convolutional Neural Networks with Test-Time Augmentation","created":"2018-10-18","cited_by_count":36},{"id":"2104.09732","title":"Knowledge Distillation as Semiparametric Inference","created":"2021-04-20","cited_by_count":29},{"id":"1908.07235","title":"Density estimation in representation space to predict model uncertainty","created":"2019-08-20","cited_by_count":27},{"id":"2110.14149","title":"Diversity Matters When Learning From Ensembles","created":"2021-10-27","cited_by_count":27},{"id":"1809.10877","title":"Learning for Single-Shot Confidence Calibration in Deep Neural Networks through Stochastic Inferences","created":"2018-09-28","cited_by_count":25},{"id":"1912.07458","title":"On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration","created":"2019-12-16","cited_by_count":18},{"id":"1805.01811","title":"Failure Prediction for Autonomous Driving","created":"2018-05-04","cited_by_count":14},{"id":"2110.03135","title":"Label Noise in Adversarial Training: A Novel Perspective to Study Robust Overfitting","created":"2021-10-07","cited_by_count":14},{"id":"2205.12528","title":"LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text Classification","created":"2022-05-25","cited_by_count":11},{"id":"1506.07224","title":"Deep CNN Ensemble with Data Augmentation for Object Detection","created":"2015-06-24","cited_by_count":10},{"id":"1809.10562","title":"Dropout Distillation for Efficiently Estimating Model Confidence","created":"2018-09-27","cited_by_count":9},{"id":"2206.06661","title":"Toward Student-Oriented Teacher Network Training For Knowledge Distillation","created":"2022-06-14","cited_by_count":7},{"id":"2102.07437","title":"Data Quality Matters For Adversarial Training: An Empirical Study","created":"2021-02-15","cited_by_count":6},{"id":"2003.11266","title":"Auto-Ensemble: An Adaptive Learning Rate Scheduling based Deep Learning Model Ensembling","created":"2020-03-25","cited_by_count":4}],"next_cursor":null}