{"list":"other","total":60,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"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":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"1807.03888","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","created":"2018-07-10","cited_by_count":1485},{"id":"1912.02762","title":"Normalizing Flows for Probabilistic Modeling and Inference","created":"2019-12-05","cited_by_count":1323},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"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":"1806.01768","title":"Evidential Deep Learning to Quantify Classification Uncertainty","created":"2018-06-05","cited_by_count":732},{"id":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"id":"1809.11165","title":"GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration","created":"2018-09-28","cited_by_count":609},{"id":"2204.06507","title":"Out-of-Distribution Detection with Deep Nearest Neighbors","created":"2022-04-13","cited_by_count":600},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"1802.10501","title":"Predictive Uncertainty Estimation via Prior Networks","created":"2018-02-28","cited_by_count":557},{"id":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"id":"1810.09136","title":"Do Deep Generative Models Know What They Don't Know?","created":"2018-10-22","cited_by_count":443},{"id":"1807.00263","title":"Accurate Uncertainties for Deep Learning Using Calibrated Regression","created":"2018-07-01","cited_by_count":422},{"id":"1805.10965","title":"Lipschitz regularity of deep neural networks: analysis and efficient estimation","created":"2018-05-28","cited_by_count":415},{"id":"2203.10807","title":"ViM: Out-Of-Distribution with Virtual-logit Matching","created":"2022-03-21","cited_by_count":405},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390},{"id":"2006.10108","title":"Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness","created":"2020-06-17","cited_by_count":389},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"1804.04368","title":"Regularisation of Neural Networks by Enforcing Lipschitz Continuity","created":"2018-04-12","cited_by_count":314},{"id":"1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","created":"2015-02-19","cited_by_count":284},{"id":"2205.09310","title":"Mitigating Neural Network Overconfidence with Logit Normalization","created":"2022-05-19","cited_by_count":252},{"id":"2002.10118","title":"Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks","created":"2020-02-24","cited_by_count":231},{"id":"1705.07832","title":"Concrete Dropout","created":"2017-05-22","cited_by_count":227},{"id":"1806.00451","title":"Do CIFAR-10 Classifiers Generalize to CIFAR-10?","created":"2018-06-01","cited_by_count":200},{"id":"2102.11582","title":"Deep Deterministic Uncertainty: A Simple Baseline","created":"2021-02-23","cited_by_count":200},{"id":"1802.04034","title":"Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks","created":"2018-02-12","cited_by_count":195},{"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":"1802.09127","title":"Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling","created":"2018-02-26","cited_by_count":169},{"id":"2006.09239","title":"Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts","created":"2020-06-16","cited_by_count":164},{"id":"1512.05287","title":"A Theoretically Grounded Application of Dropout in Recurrent Neural Networks","created":"2015-12-16","cited_by_count":161},{"id":"1905.00076","title":"Ensemble Distribution Distillation","created":"2019-04-30","cited_by_count":158},{"id":"1803.04386","title":"Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches","created":"2018-03-12","cited_by_count":133},{"id":"1905.13472","title":"Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness","created":"2019-05-31","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":"2108.00106","title":"Soft Calibration Objectives for Neural Networks","created":"2021-07-30","cited_by_count":92},{"id":"1905.06023","title":"Distribution Calibration for Regression","created":"2019-05-15","cited_by_count":89},{"id":"1911.00937","title":"Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks","created":"2019-11-03","cited_by_count":87},{"id":"2110.09410","title":"Exploiting Domain-Specific Features to Enhance Domain Generalization","created":"2021-10-18","cited_by_count":86},{"id":"2006.06049","title":"On Mixup Regularization","created":"2020-06-10","cited_by_count":83},{"id":"2106.04015","title":"Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning","created":"2021-06-07","cited_by_count":82},{"id":"1909.12180","title":"Towards neural networks that provably know when they don't know","created":"2019-09-26","cited_by_count":69},{"id":"2211.00151","title":"A Close Look into the Calibration of Pre-trained Language Models","created":"2022-10-31","cited_by_count":57},{"id":"2010.14986","title":"Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?","created":"2020-10-28","cited_by_count":39},{"id":"2105.10305","title":"Correlated Input-Dependent Label Noise in Large-Scale Image Classification","created":"2021-05-19","cited_by_count":37},{"id":"2202.03101","title":"Nonparametric Uncertainty Quantification for Single Deterministic Neural Network","created":"2022-02-07","cited_by_count":36},{"id":"2112.07184","title":"Calibrated and Sharp Uncertainties in Deep Learning via Density Estimation","created":"2021-12-14","cited_by_count":33},{"id":"2104.05097","title":"Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks","created":"2021-04-11","cited_by_count":30},{"id":"2005.08110","title":"Generalized Bayesian Posterior Expectation Distillation for Deep Neural Networks","created":"2020-05-16","cited_by_count":14}],"next_cursor":null}