{"list":"other","total":68,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"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":"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":"1506.03365","title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop","created":"2015-06-10","cited_by_count":1355},{"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":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"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":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"1801.04062","title":"MINE: Mutual Information Neural Estimation","created":"2018-01-12","cited_by_count":683},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"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":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"id":"2004.05498","title":"FDA: Fourier Domain Adaptation for Semantic Segmentation","created":"2020-04-11","cited_by_count":541},{"id":"1606.00709","title":"f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization","created":"2016-06-02","cited_by_count":506},{"id":"1904.01685","title":"Measuring Calibration in Deep Learning","created":"2019-04-02","cited_by_count":446},{"id":"1704.00109","title":"Snapshot Ensembles: Train 1, get M for free","created":"2017-04-01","cited_by_count":350},{"id":"1802.04865","title":"Learning Confidence for Out-of-Distribution Detection in Neural Networks","created":"2018-02-13","cited_by_count":245},{"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":"1902.03932","title":"Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning","created":"2019-02-11","cited_by_count":203},{"id":"1806.04606","title":"Knowledge Distillation by On-the-Fly Native Ensemble","created":"2018-06-12","cited_by_count":186},{"id":"1504.06755","title":"TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking","created":"2015-04-25","cited_by_count":165},{"id":"1910.06222","title":"Understanding the Limitations of Variational Mutual Information Estimators","created":"2019-10-14","cited_by_count":140},{"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":"1912.00350","title":"Online Knowledge Distillation with Diverse Peers","created":"2019-12-01","cited_by_count":128},{"id":"1910.07162","title":"Conditional Learning of Fair Representations","created":"2019-10-16","cited_by_count":78},{"id":"1606.07839","title":"Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles","created":"2016-06-24","cited_by_count":77},{"id":"2002.05379","title":"The Conditional Entropy Bottleneck","created":"2020-02-13","cited_by_count":75},{"id":"1903.11341","title":"Diversity with Cooperation: Ensemble Methods for Few-Shot Classification","created":"2019-03-27","cited_by_count":70},{"id":"1805.11761","title":"Collaborative Learning for Deep Neural Networks","created":"2018-05-30","cited_by_count":69},{"id":"1901.09981","title":"Improving Adversarial Robustness of Ensembles with Diversity Training","created":"2019-01-28","cited_by_count":69},{"id":"1610.04490","title":"Amortised MAP Inference for Image Super-resolution","created":"2016-10-14","cited_by_count":68},{"id":"1902.00038","title":"BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection","created":"2019-01-31","cited_by_count":62},{"id":"2002.01775","title":"Feature-map-level Online Adversarial Knowledge Distillation","created":"2020-02-05","cited_by_count":62},{"id":"2006.04147","title":"Peer Collaborative Learning for Online Knowledge Distillation","created":"2020-06-07","cited_by_count":58},{"id":"1804.00382","title":"Attention-based Ensemble for Deep Metric Learning","created":"2018-04-02","cited_by_count":56},{"id":"1904.09058","title":"Feature Fusion for Online Mutual Knowledge Distillation","created":"2019-04-19","cited_by_count":40},{"id":"1807.00906","title":"Uncertainty in the Variational Information Bottleneck","created":"2018-07-02","cited_by_count":39},{"id":"1906.01824","title":"CCMI : Classifier based Conditional Mutual Information Estimation","created":"2019-06-05","cited_by_count":37},{"id":"2006.06752","title":"An Unsupervised Information-Theoretic Perceptual Quality Metric","created":"2020-06-11","cited_by_count":28},{"id":"2003.04514","title":"Diversity inducing Information Bottleneck in Model Ensembles","created":"2020-03-10","cited_by_count":27},{"id":"1911.10688","title":"Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator","created":"2019-11-25","cited_by_count":25},{"id":"1907.07331","title":"Learnability for the Information Bottleneck","created":"2019-07-17","cited_by_count":24},{"id":"2007.04206","title":"Diverse Ensembles Improve Calibration","created":"2020-07-08","cited_by_count":23},{"id":"1911.01291","title":"Ensembles of Locally Independent Prediction Models","created":"2019-11-04","cited_by_count":22},{"id":"1605.06465","title":"Swapout: Learning an ensemble of deep architectures","created":"2016-05-20","cited_by_count":19},{"id":"2003.12537","title":"Unpacking Information Bottlenecks: Unifying Information-Theoretic Objectives in Deep Learning","created":"2020-03-27","cited_by_count":16},{"id":"1604.03006","title":"Demystifying Fixed k-Nearest Neighbor Information Estimators","created":"2016-04-11","cited_by_count":14},{"id":"2002.05380","title":"CEB Improves Model Robustness","created":"2020-02-13","cited_by_count":14},{"id":"1802.07881","title":"Diversity regularization in deep ensembles","created":"2018-02-22","cited_by_count":11},{"id":"2001.01878","title":"Phase Transitions for the Information Bottleneck in Representation Learning","created":"2020-01-07","cited_by_count":11},{"id":"2006.07225","title":"Neural Estimators for Conditional Mutual Information Using Nearest Neighbors Sampling","created":"2020-06-12","cited_by_count":7},{"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":"1804.10988","title":"SHADE: Information Based Regularization for Deep Learning","created":"2018-04-29","cited_by_count":3},{"id":"2003.01474","title":"Anytime Inference with Distilled Hierarchical Neural Ensembles","created":"2020-03-03","cited_by_count":3},{"id":"2006.08334","title":"StackOverflow vs Kaggle: A Study of Developer Discussions About Data Science","created":"2020-06-06","cited_by_count":3},{"id":"1910.06816","title":"REVE: Regularizing Deep Learning with Variational Entropy Bound","created":"2019-10-15","cited_by_count":1}],"next_cursor":null}