{"list":"other","total":97,"rows":[{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"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":"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":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"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":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"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":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"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":"1410.8516","title":"NICE: Non-linear Independent Components Estimation","created":"2014-10-30","cited_by_count":1058},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"1812.04606","title":"Deep Anomaly Detection with Outlier Exposure","created":"2018-12-11","cited_by_count":942},{"id":"1412.1897","title":"Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images","created":"2014-12-05","cited_by_count":776},{"id":"1806.01768","title":"Evidential Deep Learning to Quantify Classification Uncertainty","created":"2018-06-05","cited_by_count":732},{"id":"1802.10501","title":"Predictive Uncertainty Estimation via Prior Networks","created":"2018-02-28","cited_by_count":557},{"id":"1511.06233","title":"Towards Open Set Deep Networks","created":"2015-11-19","cited_by_count":538},{"id":"1907.04809","title":"Variational Autoencoders and Nonlinear ICA: A Unifying Framework","created":"2019-07-10","cited_by_count":503},{"id":"2002.08791","title":"Bayesian Deep Learning and a Probabilistic Perspective of Generalization","created":"2020-02-20","cited_by_count":480},{"id":"1906.02845","title":"Likelihood Ratios for Out-of-Distribution Detection","created":"2019-06-07","cited_by_count":453},{"id":"1904.01685","title":"Measuring Calibration in Deep Learning","created":"2019-04-02","cited_by_count":446},{"id":"1511.02222","title":"Deep Kernel Learning","created":"2015-11-06","cited_by_count":445},{"id":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","created":"2019-12-05","cited_by_count":443},{"id":"1711.09325","title":"Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples","created":"2017-11-26","cited_by_count":389},{"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":"1909.02027","title":"An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction","created":"2019-09-04","cited_by_count":386},{"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":"1811.00995","title":"Invertible Residual Networks","created":"2018-11-02","cited_by_count":365},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"1412.8690","title":"Breaking the Curse of Dimensionality with Convex Neural Networks","created":"2014-12-30","cited_by_count":331},{"id":"1812.05720","title":"Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem","created":"2018-12-13","cited_by_count":323},{"id":"1804.04368","title":"Regularisation of Neural Networks by Enforcing Lipschitz Continuity","created":"2018-04-12","cited_by_count":314},{"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":"1812.02230","title":"Towards a Definition of Disentangled Representations","created":"2018-12-05","cited_by_count":296},{"id":"1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","created":"2015-02-19","cited_by_count":284},{"id":"2002.10118","title":"Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks","created":"2020-02-24","cited_by_count":231},{"id":"1411.2005","title":"Scalable Variational Gaussian Process Classification","created":"2014-11-07","cited_by_count":228},{"id":"1905.12558","title":"Limitations of the Empirical Fisher Approximation for Natural Gradient Descent","created":"2019-05-29","cited_by_count":217},{"id":"1811.05381","title":"Sorting out Lipschitz function approximation","created":"2018-11-13","cited_by_count":213},{"id":"2106.09022","title":"A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection","created":"2021-06-16","cited_by_count":207},{"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":"1801.10578","title":"Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach","created":"2018-01-31","cited_by_count":182},{"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":"1906.02506","title":"Practical Deep Learning with Bayesian Principles","created":"2019-06-06","cited_by_count":158},{"id":"1705.08933","title":"Doubly Stochastic Variational Inference for Deep Gaussian Processes","created":"2017-05-24","cited_by_count":143},{"id":"1802.07088","title":"i-RevNet: Deep Invertible Networks","created":"2018-02-20","cited_by_count":137},{"id":"1605.08254","title":"Robust Large Margin Deep Neural Networks","created":"2016-05-26","cited_by_count":118},{"id":"1709.08716","title":"DOC: Deep Open Classification of Text Documents","created":"2017-09-25","cited_by_count":109},{"id":"2004.11154","title":"Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond","created":"2020-04-23","cited_by_count":109},{"id":"2008.11865","title":"Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra","created":"2020-08-27","cited_by_count":94},{"id":"1611.00336","title":"Stochastic Variational Deep Kernel Learning","created":"2016-11-01","cited_by_count":93},{"id":"1805.02242","title":"Reachability Analysis of Deep Neural Networks with Provable Guarantees","created":"2018-05-06","cited_by_count":93},{"id":"1610.09072","title":"Orthogonal Random Features","created":"2016-10-28","cited_by_count":91},{"id":"1906.01930","title":"Approximate Inference Turns Deep Networks into Gaussian Processes","created":"2019-06-05","cited_by_count":89},{"id":"2102.11409","title":"On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty","created":"2021-02-22","cited_by_count":87},{"id":"2004.13820","title":"Evolution of Semantic Similarity -- A Survey","created":"2020-04-19","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":"1402.5876","title":"Manifold Gaussian Processes for Regression","created":"2014-02-24","cited_by_count":80},{"id":"2006.09347","title":"Understanding and Mitigating Exploding Inverses in Invertible Neural Networks","created":"2020-06-16","cited_by_count":71},{"id":"1909.12180","title":"Towards neural networks that provably know when they don't know","created":"2019-09-26","cited_by_count":69},{"id":"2104.03829","title":"Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditions","created":"2021-04-08","cited_by_count":68},{"id":"1811.00401","title":"Excessive Invariance Causes Adversarial Vulnerability","created":"2018-11-01","cited_by_count":66},{"id":"1906.03260","title":"Reliable training and estimation of variance networks","created":"2019-06-04","cited_by_count":63},{"id":"1909.03862","title":"Out-of-domain Detection for Natural Language Understanding in Dialog Systems","created":"2019-09-09","cited_by_count":62},{"id":"1707.02476","title":"Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks","created":"2017-07-08","cited_by_count":48},{"id":"2006.16649","title":"Sparse Gaussian Processes with Spherical Harmonic Features","created":"2020-06-30","cited_by_count":43},{"id":"2003.01227","title":"Fast Predictive Uncertainty for Classification with Bayesian Deep Networks","created":"2020-03-02","cited_by_count":31},{"id":"2007.05134","title":"Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks","created":"2020-07-10","cited_by_count":31},{"id":"2010.02720","title":"Learnable Uncertainty under Laplace Approximations","created":"2020-10-06","cited_by_count":29},{"id":"2111.03577","title":"Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning","created":"2021-11-05","cited_by_count":25},{"id":"2111.12951","title":"Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift","created":"2021-11-25","cited_by_count":22},{"id":"1703.00091","title":"Semi-analytical approximations to statistical moments of sigmoid and softmax mappings of normal variables","created":"2017-03-01","cited_by_count":20},{"id":"2107.04212","title":"Measuring and Improving Model-Moderator Collaboration using Uncertainty Estimation","created":"2021-07-09","cited_by_count":18},{"id":"1604.02313","title":"Norm-preserving Orthogonal Permutation Linear Unit Activation Functions (OPLU)","created":"2016-04-08","cited_by_count":16},{"id":"2006.07584","title":"Mean-Field Approximation to Gaussian-Softmax Integral with Application to Uncertainty Estimation","created":"2020-06-13","cited_by_count":16},{"id":"1804.05012","title":"Representing smooth functions as compositions of near-identity functions with implications for deep network optimization","created":"2018-04-13","cited_by_count":15},{"id":"2106.10065","title":"Being a Bit Frequentist Improves Bayesian Neural Networks","created":"2021-06-18","cited_by_count":15},{"id":"1805.10522","title":"Calibrating Deep Convolutional Gaussian Processes","created":"2018-05-26","cited_by_count":13},{"id":"1904.08524","title":"Towards Open Intent Discovery for Conversational Text","created":"2019-04-17","cited_by_count":13},{"id":"2105.14399","title":"Enhanced Isotropy Maximization Loss: Seamless and High-Performance Out-of-Distribution Detection Simply Replacing the SoftMax Loss","created":"2021-05-30","cited_by_count":11},{"id":"1903.10484","title":"Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness","created":"2019-03-25","cited_by_count":9},{"id":"2106.02469","title":"Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective","created":"2021-06-04","cited_by_count":7},{"id":"1812.02575","title":"Prior Networks for Detection of Adversarial Attacks","created":"2018-12-06","cited_by_count":2},{"id":"1904.02505","title":"A deterministic and computable Bernstein-von Mises theorem","created":"2019-04-04","cited_by_count":2},{"id":"1810.12278","title":"Towards Principled Uncertainty Estimation for Deep Neural Networks","created":"2018-10-29","cited_by_count":1},{"id":"2103.15041","title":"Accurate and Reliable Forecasting using Stochastic Differential Equations","created":"2021-03-28","cited_by_count":1}],"next_cursor":null}