{"list":"other","total":153,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"1607.01719","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","created":"2016-07-06","cited_by_count":1200},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1412.6806","title":"Striving for Simplicity: The All Convolutional Net","created":"2014-12-21","cited_by_count":990},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1710.03463","title":"Learning to Generalize: Meta-Learning for Domain Generalization","created":"2017-10-10","cited_by_count":763},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"1412.3756","title":"Certifying and removing disparate impact","created":"2014-12-11","cited_by_count":715},{"id":"1807.04975","title":"Recognition in Terra Incognita","created":"2018-07-13","cited_by_count":658},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"1803.02453","title":"A Reductions Approach to Fair Classification","created":"2018-03-06","cited_by_count":587},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"1501.01332","title":"Causal inference using invariant prediction: identification and confidence intervals","created":"2015-01-06","cited_by_count":536},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"2008.02217","title":"Hopfield Networks is All You Need","created":"2020-07-16","cited_by_count":475},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1805.12018","title":"Generalizing to Unseen Domains via Adversarial Data Augmentation","created":"2018-05-30","cited_by_count":451},{"id":"1903.06864","title":"Domain Generalization by Solving Jigsaw Puzzles","created":"2019-03-16","cited_by_count":450},{"id":"2007.02454","title":"Self-Challenging Improves Cross-Domain Generalization","created":"2020-07-05","cited_by_count":426},{"id":"1910.13580","title":"Domain Generalization via Model-Agnostic Learning of Semantic Features","created":"2019-10-29","cited_by_count":407},{"id":"1709.02012","title":"On Fairness and Calibration","created":"2017-09-06","cited_by_count":406},{"id":"1711.01558","title":"Wasserstein Auto-Encoders","created":"2017-11-05","cited_by_count":373},{"id":"1610.08452","title":"Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment","created":"2016-10-26","cited_by_count":369},{"id":"1605.09522","title":"Kernel Mean Embedding of Distributions: A Review and Beyond","created":"2016-05-31","cited_by_count":364},{"id":"1709.10190","title":"Unified Deep Supervised Domain Adaptation and Generalization","created":"2017-09-28","cited_by_count":323},{"id":"1608.06019","title":"Domain Separation Networks","created":"2016-08-22","cited_by_count":320},{"id":"1612.05424","title":"Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks","created":"2016-12-16","cited_by_count":308},{"id":"2003.13216","title":"Learning to Learn Single Domain Generalization","created":"2020-03-30","cited_by_count":296},{"id":"2007.03304","title":"Learning to Generate Novel Domains for Domain Generalization","created":"2020-07-07","cited_by_count":296},{"id":"1612.07828","title":"Learning from Simulated and Unsupervised Images through Adversarial Training","created":"2016-12-22","cited_by_count":288},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"1804.10745","title":"Generalizing Across Domains via Cross-Gradient Training","created":"2018-04-28","cited_by_count":268},{"id":"1810.12890","title":"DropBlock: A regularization method for convolutional networks","created":"2018-10-30","cited_by_count":262},{"id":"1508.07680","title":"Domain Generalization for Object Recognition with Multi-task Autoencoders","created":"2015-08-31","cited_by_count":253},{"id":"1912.01805","title":"Adversarial Domain Adaptation with Domain Mixup","created":"2019-12-04","cited_by_count":250},{"id":"1902.00113","title":"Episodic Training for Domain Generalization","created":"2019-01-31","cited_by_count":245},{"id":"1711.09784","title":"Distilling a Neural Network Into a Soft Decision Tree","created":"2017-11-27","cited_by_count":236},{"id":"1710.04806","title":"Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions","created":"2017-10-13","cited_by_count":234},{"id":"2003.06054","title":"Deep Domain-Adversarial Image Generation for Domain Generalisation","created":"2020-03-12","cited_by_count":231},{"id":"1411.4280","title":"Efficient Object Localization Using Convolutional Networks","created":"2014-11-16","cited_by_count":227},{"id":"1802.08626","title":"Empirical Risk Minimization under Fairness Constraints","created":"2018-02-23","cited_by_count":226},{"id":"2006.07500","title":"Domain Generalization using Causal Matching","created":"2020-06-12","cited_by_count":225},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"1511.00830","title":"The Variational Fair Autoencoder","created":"2015-11-03","cited_by_count":223},{"id":"1605.07648","title":"FractalNet: Ultra-Deep Neural Networks without Residuals","created":"2016-05-24","cited_by_count":216},{"id":"2003.07761","title":"CycleISP: Real Image Restoration via Improved Data Synthesis","created":"2020-03-17","cited_by_count":213},{"id":"1704.04232","title":"Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization","created":"2017-04-13","cited_by_count":207},{"id":"1805.11783","title":"To Trust Or Not To Trust A Classifier","created":"2018-05-30","cited_by_count":207},{"id":"1912.08142","title":"Causality matters in medical imaging","created":"2019-12-17","cited_by_count":193},{"id":"2001.00677","title":"Improve Unsupervised Domain Adaptation with Mixup Training","created":"2020-01-03","cited_by_count":185},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"1711.07910","title":"Domain Generalization by Marginal Transfer Learning","created":"2017-11-21","cited_by_count":180},{"id":"1802.08129","title":"Multimodal Explanations: Justifying Decisions and Pointing to the Evidence","created":"2018-02-15","cited_by_count":179},{"id":"1904.07396","title":"Real Image Denoising with Feature Attention","created":"2019-04-16","cited_by_count":176},{"id":"2007.11498","title":"CrossTransformers: spatially-aware few-shot transfer","created":"2020-07-22","cited_by_count":174},{"id":"1911.07661","title":"Domain Generalization Using a Mixture of Multiple Latent Domains","created":"2019-11-18","cited_by_count":170},{"id":"1702.04595","title":"Visualizing Deep Neural Network Decisions: Prediction Difference Analysis","created":"2017-02-15","cited_by_count":166},{"id":"1607.03516","title":"Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation","created":"2016-07-12","cited_by_count":163},{"id":"1907.04275","title":"Learning to Optimize Domain Specific Normalization for Domain Generalization","created":"2019-07-09","cited_by_count":161},{"id":"2008.08290","title":"Attribute Prototype Network for Zero-Shot Learning","created":"2020-08-19","cited_by_count":160},{"id":"1603.08507","title":"Generating Visual Explanations","created":"2016-03-28","cited_by_count":158},{"id":"1807.08479","title":"Domain Generalization via Conditional Invariant Representation","created":"2018-07-23","cited_by_count":146}],"next_cursor":"100"}