{"list":"other","total":86,"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":"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":"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":"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":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"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":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"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":"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":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"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":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"2203.13591","title":"Continual Test-Time Domain Adaptation","created":"2022-03-25","cited_by_count":525},{"id":"2002.11569","title":"Overfitting in adversarially robust deep learning","created":"2020-02-26","cited_by_count":506},{"id":"2111.12797","title":"ReAct: Out-of-distribution Detection With Rectified Activations","created":"2021-11-24","cited_by_count":486},{"id":"1911.11132","title":"Scaling Out-of-Distribution Detection for Real-World Settings","created":"2019-11-25","cited_by_count":465},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434},{"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":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"2002.09437","title":"Calibrating Deep Neural Networks using Focal Loss","created":"2020-02-21","cited_by_count":357},{"id":"2110.00218","title":"On the Importance of Gradients for Detecting Distributional Shifts in the Wild","created":"2021-10-01","cited_by_count":339},{"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":"2205.09310","title":"Mitigating Neural Network Overconfidence with Logit Normalization","created":"2022-05-19","cited_by_count":252},{"id":"1706.01350","title":"Emergence of Invariance and Disentanglement in Deep Representations","created":"2017-06-05","cited_by_count":215},{"id":"2104.00466","title":"Improving Calibration for Long-Tailed Recognition","created":"2021-04-01","cited_by_count":212},{"id":"1805.11783","title":"To Trust Or Not To Trust A Classifier","created":"2018-05-30","cited_by_count":207},{"id":"1910.04851","title":"Addressing Failure Prediction by Learning Model Confidence","created":"2019-10-01","cited_by_count":186},{"id":"1704.05519","title":"Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art","created":"2017-04-18","cited_by_count":182},{"id":"2010.06610","title":"Training independent subnetworks for robust prediction","created":"2020-10-13","cited_by_count":177},{"id":"1504.06755","title":"TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking","created":"2015-04-25","cited_by_count":165},{"id":"2003.13964","title":"Regularizing Class-wise Predictions via Self-knowledge Distillation","created":"2020-03-31","cited_by_count":144},{"id":"1805.08206","title":"Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers","created":"2018-05-21","cited_by_count":113},{"id":"2007.01458","title":"Confidence-Aware Learning for Deep Neural Networks","created":"2020-07-03","cited_by_count":113},{"id":"2210.14707","title":"Is Out-of-Distribution Detection Learnable?","created":"2022-10-26","cited_by_count":109},{"id":"2006.12800","title":"Calibration of Neural Networks using Splines","created":"2020-06-23","cited_by_count":97},{"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":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82},{"id":"2001.01385","title":"Identifying and Compensating for Feature Deviation in Imbalanced Deep Learning","created":"2020-01-06","cited_by_count":76},{"id":"2103.01550","title":"Label-Imbalanced and Group-Sensitive Classification under Overparameterization","created":"2021-03-02","cited_by_count":74},{"id":"2003.06820","title":"Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks","created":"2020-03-15","cited_by_count":65},{"id":"2101.12523","title":"Optimal strategies for reject option classifiers","created":"2021-01-29","cited_by_count":61},{"id":"2102.06289","title":"When and How Mixup Improves Calibration","created":"2021-02-11","cited_by_count":60},{"id":"1906.03291","title":"Understanding Generalization through Visualizations","created":"2019-06-07","cited_by_count":54},{"id":"2104.00676","title":"Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study","created":"2021-04-01","cited_by_count":51},{"id":"2111.09030","title":"Trustworthy Long-Tailed Classification","created":"2021-11-17","cited_by_count":51},{"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":"2010.09875","title":"Combining Ensembles and Data Augmentation can Harm your Calibration","created":"2020-10-19","cited_by_count":44},{"id":"2303.02970","title":"Rethinking Confidence Calibration for Failure Prediction","created":"2023-03-06","cited_by_count":43},{"id":"2303.17093","title":"OpenMix: Exploring Outlier Samples for Misclassification Detection","created":"2023-03-30","cited_by_count":38},{"id":"2012.06508","title":"Confidence Estimation via Auxiliary Models","created":"2020-12-11","cited_by_count":34},{"id":"2210.16315","title":"Beyond calibration: estimating the grouping loss of modern neural networks","created":"2022-10-28","cited_by_count":32},{"id":"2006.13092","title":"Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning","created":"2020-06-23","cited_by_count":27},{"id":"2403.01759","title":"Open-world machine learning: A review and new outlooks","created":"2024-03-04","cited_by_count":27},{"id":"2008.03033","title":"Evaluating probabilistic classifiers: Reliability diagrams and score decompositions revisited","created":"2020-08-07","cited_by_count":26},{"id":"2006.07897","title":"Entropic gradient descent algorithms and wide flat minima","created":"2020-06-14","cited_by_count":25},{"id":"1912.01730","title":"Distance-Based Learning from Errors for Confidence Calibration","created":"2019-12-03","cited_by_count":23},{"id":"2206.09880","title":"Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities","created":"2022-06-20","cited_by_count":23},{"id":"2207.06873","title":"BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks","created":"2022-07-14","cited_by_count":23},{"id":"2011.09172","title":"On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective","created":"2020-11-18","cited_by_count":21},{"id":"2303.01201","title":"Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection","created":"2023-03-02","cited_by_count":14},{"id":"2307.09165","title":"Towards Trustworthy Dataset Distillation","created":"2023-07-18","cited_by_count":14},{"id":"2102.11402","title":"MixUp Training Leads to Reduced Overfitting and Improved Calibration for the Transformer Architecture","created":"2021-02-22","cited_by_count":11},{"id":"2110.00054","title":"Learning to Predict Trustworthiness with Steep Slope Loss","created":"2021-09-30","cited_by_count":11},{"id":"2311.13355","title":"Unified Classification and Rejection: A One-versus-All Framework","created":"2023-11-22","cited_by_count":9}],"next_cursor":null}