{"list":"other","total":60,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"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":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1805.07836","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","created":"2018-05-20","cited_by_count":997},{"id":"1803.09050","title":"Learning to Reweight Examples for Robust Deep Learning","created":"2018-03-24","cited_by_count":675},{"id":"1801.07593","title":"Mitigating Unwanted Biases with Adversarial Learning","created":"2018-01-22","cited_by_count":663},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"1707.09457","title":"Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints","created":"2017-07-29","cited_by_count":420},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367},{"id":"2006.07710","title":"The Pitfalls of Simplicity Bias in Neural Networks","created":"2020-06-13","cited_by_count":351},{"id":"2110.01963","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","created":"2021-10-05","cited_by_count":327},{"id":"2010.07249","title":"Environment Inference for Invariant Learning","created":"2020-10-14","cited_by_count":306},{"id":"2011.09468","title":"Gradient Starvation: A Learning Proclivity in Neural Networks","created":"2020-11-18","cited_by_count":267},{"id":"2006.16923","title":"Large image datasets: A pyrrhic win for computer vision?","created":"2020-06-24","cited_by_count":237},{"id":"1803.09797","title":"Women also Snowboard: Overcoming Bias in Captioning Models","created":"2018-03-26","cited_by_count":236},{"id":"1805.12317","title":"Multiaccuracy: Black-Box Post-Processing for Fairness in Classification","created":"2018-05-31","cited_by_count":222},{"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":"1910.02806","title":"Learning De-biased Representations with Biased Representations","created":"2019-10-07","cited_by_count":199},{"id":"1610.03425","title":"Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach","created":"2016-10-11","cited_by_count":183},{"id":"1805.08522","title":"Deep learning generalizes because the parameter-function map is biased towards simple functions","created":"2018-05-22","cited_by_count":183},{"id":"2010.05893","title":"Large-Scale Methods for Distributionally Robust Optimization","created":"2020-10-12","cited_by_count":179},{"id":"2007.03051","title":"Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models","created":"2020-07-06","cited_by_count":169},{"id":"2203.14960","title":"Domino: Discovering Systematic Errors with Cross-Modal Embeddings","created":"2022-03-24","cited_by_count":156},{"id":"1906.02659","title":"Does Object Recognition Work for Everyone?","created":"2019-06-06","cited_by_count":151},{"id":"2008.02312","title":"Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs","created":"2020-08-05","cited_by_count":151},{"id":"1901.04407","title":"Self-Driving Cars: A Survey","created":"2019-01-14","cited_by_count":148},{"id":"1909.02060","title":"Distributionally Robust Language Modeling","created":"2019-09-04","cited_by_count":143},{"id":"2004.07999","title":"REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets","created":"2020-04-16","cited_by_count":136},{"id":"1810.03649","title":"Overcoming Language Priors in Visual Question Answering with Adversarial Regularization","created":"2018-10-08","cited_by_count":105},{"id":"2001.03152","title":"Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias","created":"2020-01-09","cited_by_count":91},{"id":"2204.02070","title":"Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation","created":"2022-04-05","cited_by_count":88},{"id":"1505.01257","title":"A Deeper Look at Dataset Bias","created":"2015-05-06","cited_by_count":87},{"id":"2212.04825","title":"A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others","created":"2022-12-09","cited_by_count":85},{"id":"2107.07919","title":"A Survey on Bias in Visual Datasets","created":"2021-07-16","cited_by_count":84},{"id":"2210.00055","title":"MaskTune: Mitigating Spurious Correlations by Forcing to Explore","created":"2022-09-30","cited_by_count":66},{"id":"2107.00758","title":"The Spotlight: A General Method for Discovering Systematic Errors in Deep Learning Models","created":"2021-07-01","cited_by_count":63},{"id":"2102.12594","title":"Directional Bias Amplification","created":"2021-02-24","cited_by_count":54},{"id":"2309.08534","title":"Towards Last-layer Retraining for Group Robustness with Fewer Annotations","created":"2023-09-15","cited_by_count":54},{"id":"2207.10077","title":"Discover and Mitigate Unknown Biases with Debiasing Alternate Networks","created":"2022-07-20","cited_by_count":47},{"id":"2309.16928","title":"Learning to Receive Help: Intervention-Aware Concept Embedding Models","created":"2023-09-29","cited_by_count":41},{"id":"2303.06167","title":"Overwriting Pretrained Bias with Finetuning Data","created":"2023-03-10","cited_by_count":32},{"id":"2309.17430","title":"FACTS: First Amplify Correlations and Then Slice to Discover Bias","created":"2023-09-29","cited_by_count":26},{"id":"2310.18555","title":"Group Robust Classification Without Any Group Information","created":"2023-10-28","cited_by_count":25},{"id":"2106.06620","title":"Robust Representation Learning via Perceptual Similarity Metrics","created":"2021-06-11","cited_by_count":23},{"id":"2210.11924","title":"Men Also Do Laundry: Multi-Attribute Bias Amplification","created":"2022-10-21","cited_by_count":21},{"id":"2309.08825","title":"Distributionally Robust Post-hoc Classifiers under Prior Shifts","created":"2023-09-16","cited_by_count":16},{"id":"2204.02426","title":"OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses","created":"2022-04-05","cited_by_count":11},{"id":"2212.00921","title":"AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization","created":"2022-12-02","cited_by_count":10},{"id":"2312.03151","title":"Multitask Learning Can Improve Worst-Group Outcomes","created":"2023-12-05","cited_by_count":1}],"next_cursor":null}