{"list":"other","total":71,"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":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"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":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"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":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"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":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"2011.06225","title":"A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges","created":"2020-11-12","cited_by_count":819},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"1906.05271","title":"Does Learning Require Memorization? A Short Tale about a Long Tail","created":"2019-06-12","cited_by_count":460},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":445},{"id":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","created":"2019-12-05","cited_by_count":443},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249},{"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":"1806.00451","title":"Do CIFAR-10 Classifiers Generalize to CIFAR-10?","created":"2018-06-01","cited_by_count":200},{"id":"1806.04606","title":"Knowledge Distillation by On-the-Fly Native Ensemble","created":"2018-06-12","cited_by_count":186},{"id":"2203.05556","title":"On Embeddings for Numerical Features in Tabular Deep Learning","created":"2022-03-10","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":"1610.02915","title":"Deep Pyramidal Residual Networks","created":"2016-10-10","cited_by_count":163},{"id":"2006.13570","title":"Hyperparameter Ensembles for Robustness and Uncertainty Quantification","created":"2020-06-24","cited_by_count":150},{"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":"2006.07322","title":"Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks","created":"2020-06-12","cited_by_count":138},{"id":"2106.11642","title":"Repulsive Deep Ensembles are Bayesian","created":"2021-06-22","cited_by_count":104},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102},{"id":"1807.01697","title":"Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations","created":"2018-07-04","cited_by_count":99},{"id":"2007.08558","title":"On Robustness and Transferability of Convolutional Neural Networks","created":"2020-07-16","cited_by_count":98},{"id":"2003.01054","title":"Double Trouble in Double Descent : Bias and Variance(s) in the Lazy Regime","created":"2020-03-02","cited_by_count":95},{"id":"1705.07485","title":"Shake-Shake regularization","created":"2017-05-21","cited_by_count":87},{"id":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83},{"id":"2006.16736","title":"Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency","created":"2020-06-30","cited_by_count":78},{"id":"2011.03321","title":"Understanding Double Descent Requires a Fine-Grained Bias-Variance Decomposition","created":"2020-11-04","cited_by_count":76},{"id":"2301.03962","title":"A Unified Theory of Diversity in Ensemble Learning","created":"2023-01-10","cited_by_count":71},{"id":"2202.04414","title":"Agree to Disagree: Diversity through Disagreement for Better Transferability","created":"2022-02-09","cited_by_count":70},{"id":"1901.09981","title":"Improving Adversarial Robustness of Ensembles with Diversity Training","created":"2019-01-28","cited_by_count":69},{"id":"1810.08591","title":"A Modern Take on the Bias-Variance Tradeoff in Neural Networks","created":"2018-10-19","cited_by_count":65},{"id":"2202.06985","title":"Deep Ensembles Work, But Are They Necessary?","created":"2022-02-14","cited_by_count":63},{"id":"2110.12899","title":"No One Representation to Rule Them All: Overlapping Features of Training Methods","created":"2021-10-20","cited_by_count":58},{"id":"2202.03418","title":"Diversify and Disambiguate: Learning From Underspecified Data","created":"2022-02-07","cited_by_count":56},{"id":"2101.05544","title":"DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation","created":"2021-01-14","cited_by_count":48},{"id":"1905.12580","title":"Model Similarity Mitigates Test Set Overuse","created":"2019-05-29","cited_by_count":38},{"id":"2110.13786","title":"Diversity and Generalization in Neural Network Ensembles","created":"2021-10-26","cited_by_count":32},{"id":"1906.07380","title":"Maximizing Overall Diversity for Improved Uncertainty Estimates in Deep Ensembles","created":"2019-06-18","cited_by_count":30},{"id":"2211.05641","title":"Regression as Classification: Influence of Task Formulation on Neural Network Features","created":"2022-11-10","cited_by_count":29},{"id":"2003.04514","title":"Diversity inducing Information Bottleneck in Model Ensembles","created":"2020-03-10","cited_by_count":27},{"id":"2007.08483","title":"On Power Laws in Deep Ensembles","created":"2020-07-16","cited_by_count":26},{"id":"2111.13011","title":"Transferability Metrics for Selecting Source Model Ensembles","created":"2021-11-25","cited_by_count":24},{"id":"2206.00050","title":"FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation","created":"2022-05-31","cited_by_count":24},{"id":"2301.11323","title":"Joint Training of Deep Ensembles Fails Due to Learner Collusion","created":"2023-01-26","cited_by_count":23},{"id":"1911.01291","title":"Ensembles of Locally Independent Prediction Models","created":"2019-11-04","cited_by_count":22},{"id":"2012.15483","title":"Why do classifier accuracies show linear trends under distribution shift?","created":"2020-12-31","cited_by_count":21},{"id":"2005.00570","title":"When Ensembling Smaller Models is More Efficient than Single Large Models","created":"2020-05-01","cited_by_count":20},{"id":"2010.06866","title":"Deep Ensembles for Low-Data Transfer Learning","created":"2020-10-14","cited_by_count":19},{"id":"2011.02952","title":"Generalized Negative Correlation Learning for Deep Ensembling","created":"2020-11-05","cited_by_count":17},{"id":"2011.14660","title":"Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training","created":"2020-11-30","cited_by_count":12},{"id":"2012.05825","title":"Semi-supervised novelty detection using ensembles with regularized disagreement","created":"2020-12-10","cited_by_count":7},{"id":"2006.11695","title":"Uncertainty-Aware (UNA) Bases for Deep Bayesian Regression Using Multi-Headed Auxiliary Networks","created":"2020-06-21","cited_by_count":6},{"id":"2202.08376","title":"How to Fill the Optimum Set? Population Gradient Descent with Harmless Diversity","created":"2022-02-16","cited_by_count":4},{"id":"2110.04274","title":"Kernel Interpolation as a Bayes Point Machine","created":"2021-10-08","cited_by_count":1}],"next_cursor":null}