{"list":"other","total":88,"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":"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"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":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"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":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"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":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"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":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"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":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"2009.07896","title":"Captum: A unified and generic model interpretability library for PyTorch","created":"2020-09-16","cited_by_count":547},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"1509.06321","title":"Evaluating the visualization of what a Deep Neural Network has learned","created":"2015-09-21","cited_by_count":419},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"1807.00431","title":"Confounding variables can degrade generalization performance of radiological deep learning models","created":"2018-07-02","cited_by_count":379},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"1711.10160","title":"Snorkel: Rapid Training Data Creation with Weak Supervision","created":"2017-11-28","cited_by_count":372},{"id":"1902.10178","title":"Unmasking Clever Hans Predictors and Assessing What Machines Really Learn","created":"2019-02-26","cited_by_count":365},{"id":"1706.07979","title":"Methods for Interpreting and Understanding Deep Neural Networks","created":"2017-06-24","cited_by_count":345},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"1711.02173","title":"Synthetic and Natural Noise Both Break Neural Machine Translation","created":"2017-11-06","cited_by_count":306},{"id":"1711.10337","title":"Are GANs Created Equal? A Large-Scale Study","created":"2017-11-28","cited_by_count":267},{"id":"1808.01204","title":"Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data","created":"2018-08-03","cited_by_count":261},{"id":"1605.07723","title":"Data Programming: Creating Large Training Sets, Quickly","created":"2016-05-25","cited_by_count":246},{"id":"1909.12475","title":"Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging","created":"2019-09-27","cited_by_count":216},{"id":"2011.12945","title":"No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems","created":"2020-11-25","cited_by_count":209},{"id":"2103.03098","title":"Accounting for Variance in Machine Learning Benchmarks","created":"2021-03-01","cited_by_count":201},{"id":"1605.09304","title":"Synthesizing the preferred inputs for neurons in neural networks via deep generator networks","created":"2016-05-30","cited_by_count":181},{"id":"1909.03004","title":"Show Your Work: Improved Reporting of Experimental Results","created":"2019-09-06","cited_by_count":169},{"id":"1702.04595","title":"Visualizing Deep Neural Network Decisions: Prediction Difference Analysis","created":"2017-02-15","cited_by_count":166},{"id":"1604.04326","title":"Improving the Robustness of Deep Neural Networks via Stability Training","created":"2016-04-15","cited_by_count":156},{"id":"2010.06595","title":"With Little Power Comes Great Responsibility","created":"2020-10-13","cited_by_count":142},{"id":"1705.02498","title":"A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortions","created":"2017-05-06","cited_by_count":108},{"id":"1807.03341","title":"Troubling Trends in Machine Learning Scholarship","created":"2018-07-09","cited_by_count":108},{"id":"2101.04840","title":"Robustness Gym: Unifying the NLP Evaluation Landscape","created":"2021-01-13","cited_by_count":108},{"id":"1707.05589","title":"On the State of the Art of Evaluation in Neural Language Models","created":"2017-07-18","cited_by_count":104},{"id":"2004.14444","title":"The Effect of Natural Distribution Shift on Question Answering Models","created":"2020-04-29","cited_by_count":104},{"id":"1705.05598","title":"Learning how to explain neural networks: PatternNet and PatternAttribution","created":"2017-05-16","cited_by_count":84},{"id":"1909.06674","title":"A Step Toward Quantifying Independently Reproducible Machine Learning Research","created":"2019-09-14","cited_by_count":77},{"id":"1707.09861","title":"Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging","created":"2017-07-31","cited_by_count":73},{"id":"1910.09840","title":"Towards Best Practice in Explaining Neural Network Decisions with LRP","created":"2019-10-22","cited_by_count":70},{"id":"1808.04260","title":"iNNvestigate neural networks!","created":"2018-08-13","cited_by_count":58},{"id":"1903.11101","title":"Cross-Modal Data Programming Enables Rapid Medical Machine Learning","created":"2019-03-26","cited_by_count":32},{"id":"2009.13888","title":"Utility is in the Eye of the User: A Critique of NLP Leaderboards","created":"2020-09-29","cited_by_count":28},{"id":"2004.05234","title":"Attend and Decode: 4D fMRI Task State Decoding Using Attention Models","created":"2020-04-10","cited_by_count":17},{"id":"1801.09858","title":"Decoding and mapping task states of the human brain via deep learning","created":"2018-01-30","cited_by_count":16},{"id":"1810.09945","title":"Analyzing Neuroimaging Data Through Recurrent Deep Learning Models","created":"2018-10-23","cited_by_count":15},{"id":"1502.00093","title":"Deep learning of fMRI big data: a novel approach to subject-transfer decoding","created":"2015-01-31","cited_by_count":7},{"id":"1809.06035","title":"Extracting representations of cognition across neuroimaging studies improves brain decoding","created":"2018-09-17","cited_by_count":7},{"id":"1907.01953","title":"Deep Transfer Learning For Whole-Brain fMRI Analyses","created":"2019-07-02","cited_by_count":6},{"id":"1911.06813","title":"Transfer Learning of fMRI Dynamics","created":"2019-11-16","cited_by_count":3},{"id":"2010.15594","title":"Shared Space Transfer Learning for analyzing multi-site fMRI data","created":"2020-10-24","cited_by_count":2}],"next_cursor":null}