{"list":"other","total":75,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"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":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1812.04606","title":"Deep Anomaly Detection with Outlier Exposure","created":"2018-12-11","cited_by_count":942},{"id":"2107.07511","title":"A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification","created":"2021-07-15","cited_by_count":792},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"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":"1709.02012","title":"On Fairness and Calibration","created":"2017-09-06","cited_by_count":406},{"id":"2305.10425","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","created":"2023-05-17","cited_by_count":401},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390},{"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":"1706.03872","title":"Six Challenges for Neural Machine Translation","created":"2017-06-12","cited_by_count":335},{"id":"2003.07892","title":"Calibration of Pre-trained Transformers","created":"2020-03-17","cited_by_count":315},{"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":"2006.01862","title":"Consistent Estimators for Learning to Defer to an Expert","created":"2020-06-02","cited_by_count":271},{"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":"1902.06977","title":"Evaluating model calibration in classification","created":"2019-02-19","cited_by_count":168},{"id":"1905.00076","title":"Ensemble Distribution Distillation","created":"2019-04-30","cited_by_count":158},{"id":"1711.03953","title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","created":"2017-11-10","cited_by_count":152},{"id":"2007.08792","title":"Uncertainty Quantification and Deep Ensembles","created":"2020-07-17","cited_by_count":139},{"id":"2012.07923","title":"Improving model calibration with accuracy versus uncertainty optimization","created":"2020-12-14","cited_by_count":123},{"id":"2210.00045","title":"Calibrating Sequence likelihood Improves Conditional Language Generation","created":"2022-09-30","cited_by_count":121},{"id":"2012.08668","title":"Mitigating Bias in Calibration Error Estimation","created":"2020-12-15","cited_by_count":101},{"id":"2008.05105","title":"Local Temperature Scaling for Probability Calibration","created":"2020-08-12","cited_by_count":95},{"id":"2111.15430","title":"The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration","created":"2021-11-30","cited_by_count":91},{"id":"2305.19148","title":"Mitigating Label Biases for In-context Learning","created":"2023-05-28","cited_by_count":89},{"id":"2112.10327","title":"Classifier Calibration: A survey on how to assess and improve predicted class probabilities","created":"2021-12-20","cited_by_count":73},{"id":"2202.03673","title":"Calibrated Learning to Defer with One-vs-All Classifiers","created":"2022-02-08","cited_by_count":69},{"id":"1903.00802","title":"Calibration of Encoder Decoder Models for Neural Machine Translation","created":"2019-03-03","cited_by_count":68},{"id":"2102.06289","title":"When and How Mixup Improves Calibration","created":"2021-02-11","cited_by_count":60},{"id":"2205.10183","title":"Prototypical Calibration for Few-shot Learning of Language Models","created":"2022-05-20","cited_by_count":58},{"id":"2203.13834","title":"A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration","created":"2022-03-25","cited_by_count":49},{"id":"1704.02798","title":"Bayesian Recurrent Neural Networks","created":"2017-04-10","cited_by_count":39},{"id":"2009.04057","title":"Improved Trainable Calibration Method for Neural Networks on Medical Imaging Classification","created":"2020-09-09","cited_by_count":37},{"id":"1909.13550","title":"Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference","created":"2019-09-30","cited_by_count":36},{"id":"2203.07559","title":"On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency","created":"2022-03-14","cited_by_count":31},{"id":"2106.09613","title":"Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error","created":"2021-06-17","cited_by_count":29},{"id":"2111.00079","title":"Deep Deterministic Uncertainty for Semantic Segmentation","created":"2021-10-29","cited_by_count":24},{"id":"1908.11528","title":"Bin-wise Temperature Scaling (BTS): Improvement in Confidence Calibration Performance through Simple Scaling Techniques","created":"2019-08-30","cited_by_count":23},{"id":"1902.06579","title":"Conformal calibrators","created":"2019-02-18","cited_by_count":22},{"id":"1810.11586","title":"Attended Temperature Scaling: A Practical Approach for Calibrating Deep Neural Networks","created":"2018-10-27","cited_by_count":21},{"id":"2112.13776","title":"Transformer Uncertainty Estimation with Hierarchical Stochastic Attention","created":"2021-12-27","cited_by_count":21},{"id":"1911.00941","title":"Computationally efficient versions of conformal predictive distributions","created":"2019-11-03","cited_by_count":20},{"id":"2212.10005","title":"Calibrating Deep Neural Networks using Explicit Regularisation and Dynamic Data Pruning","created":"2022-12-20","cited_by_count":18},{"id":"2303.12748","title":"Enabling Calibration In The Zero-Shot Inference of Large Vision-Language Models","created":"2023-03-11","cited_by_count":17},{"id":"2107.09734","title":"Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutions","created":"2021-07-20","cited_by_count":16},{"id":"2302.05118","title":"Beyond In-Domain Scenarios: Robust Density-Aware Calibration","created":"2023-02-10","cited_by_count":14},{"id":"2107.13508","title":"Uncertainty-Aware Credit Card Fraud Detection Using Deep Learning","created":"2021-07-28","cited_by_count":10},{"id":"2011.12010","title":"Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs","created":"2020-11-24","cited_by_count":9},{"id":"2305.05101","title":"Towards unraveling calibration biases in medical image analysis","created":"2023-05-09","cited_by_count":8},{"id":"2306.00740","title":"On the Limitations of Temperature Scaling for Distributions with Overlaps","created":"2023-06-01","cited_by_count":7}],"next_cursor":null}