{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"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":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"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":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1812.04606","title":"Deep Anomaly Detection with Outlier Exposure","created":"2018-12-11","cited_by_count":942},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"id":"1511.07528","title":"The Limitations of Deep Learning in Adversarial Settings","created":"2015-11-24","cited_by_count":790},{"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":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"2204.06507","title":"Out-of-Distribution Detection with Deep Nearest Neighbors","created":"2022-04-13","cited_by_count":600},{"id":"1810.09136","title":"Do Deep Generative Models Know What They Don't Know?","created":"2018-10-22","cited_by_count":443},{"id":"2007.08176","title":"CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances","created":"2020-07-16","cited_by_count":441},{"id":"1702.08423","title":"Age Progression/Regression by Conditional Adversarial Autoencoder","created":"2017-02-27","cited_by_count":429},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"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":"1906.05890","title":"Gradient Descent Maximizes the Margin of Homogeneous Neural Networks","created":"2019-06-13","cited_by_count":320},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249},{"id":"2009.11848","title":"How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks","created":"2020-09-24","cited_by_count":222},{"id":"2006.06657","title":"Directional convergence and alignment in deep learning","created":"2020-06-11","cited_by_count":178},{"id":"1806.00900","title":"Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced","created":"2018-06-04","cited_by_count":177},{"id":"2008.04859","title":"BREEDS: Benchmarks for Subpopulation Shift","created":"2020-08-11","cited_by_count":155},{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154},{"id":"2010.08853","title":"From Local Structures to Size Generalization in Graph Neural Networks","created":"2020-10-17","cited_by_count":124},{"id":"1506.02617","title":"Path-SGD: Path-Normalized Optimization in Deep Neural Networks","created":"2015-06-08","cited_by_count":120},{"id":"2206.13089","title":"Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift","created":"2022-06-27","cited_by_count":94},{"id":"2110.09485","title":"Learning in High Dimension Always Amounts to Extrapolation","created":"2021-10-18","cited_by_count":66},{"id":"2106.04972","title":"Understanding Softmax Confidence and Uncertainty","created":"2021-06-09","cited_by_count":63},{"id":"2010.11748","title":"Classification with Rejection Based on Cost-sensitive Classification","created":"2020-10-22","cited_by_count":55},{"id":"2201.12760","title":"Implicit Regularization Towards Rank Minimization in ReLU Networks","created":"2022-01-30","cited_by_count":53},{"id":"2011.14654","title":"Feature Space Singularity for Out-of-Distribution Detection","created":"2020-11-30","cited_by_count":49},{"id":"1901.10655","title":"On the Calibration of Multiclass Classification with Rejection","created":"2019-01-30","cited_by_count":41},{"id":"2007.05059","title":"Learning Representations that Support Extrapolation","created":"2020-07-09","cited_by_count":36},{"id":"2203.02486","title":"The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methods","created":"2022-03-04","cited_by_count":28},{"id":"2207.07506","title":"Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data","created":"2022-07-15","cited_by_count":27},{"id":"2206.09034","title":"Towards Better Selective Classification","created":"2022-06-17","cited_by_count":25},{"id":"2302.03679","title":"How Reliable is Your Regression Model's Uncertainty Under Real-World Distribution Shifts?","created":"2023-02-07","cited_by_count":14},{"id":"2202.04302","title":"On the Implicit Bias of Gradient Descent for Temporal Extrapolation","created":"2022-02-09","cited_by_count":7},{"id":"2209.07736","title":"Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study","created":"2022-09-16","cited_by_count":7}],"next_cursor":null}