{"list":"other","total":65,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"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":"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":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"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":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"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":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"1902.10178","title":"Unmasking Clever Hans Predictors and Assessing What Machines Really Learn","created":"2019-02-26","cited_by_count":365},{"id":"1908.08474","title":"The many Shapley values for model explanation","created":"2019-08-22","cited_by_count":344},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"2006.07159","title":"Are we done with ImageNet?","created":"2020-06-12","cited_by_count":333},{"id":"1705.07857","title":"Real Time Image Saliency for Black Box Classifiers","created":"2017-05-22","cited_by_count":246},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"2011.14878","title":"Explaining by Removing: A Unified Framework for Model Explanation","created":"2020-11-21","cited_by_count":218},{"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":"2111.15667","title":"Adaptive Token Sampling For Efficient Vision Transformers","created":"2021-11-30","cited_by_count":183},{"id":"1412.6856","title":"Object Detectors Emerge in Deep Scene CNNs","created":"2014-12-22","cited_by_count":179},{"id":"1702.04595","title":"Visualizing Deep Neural Network Decisions: Prediction Difference Analysis","created":"2017-02-15","cited_by_count":166},{"id":"2106.12620","title":"IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers","created":"2021-06-23","cited_by_count":127},{"id":"2110.04301","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","created":"2021-10-08","cited_by_count":114},{"id":"2106.03149","title":"Large-scale Unsupervised Semantic Segmentation","created":"2021-06-06","cited_by_count":101},{"id":"1910.12336","title":"CXPlain: Causal Explanations for Model Interpretation under Uncertainty","created":"2019-10-27","cited_by_count":98},{"id":"2409.00729","title":"ContextCite: Attributing Model Generation to Context","created":"2024-09-01","cited_by_count":98},{"id":"2006.01272","title":"Shapley explainability on the data manifold","created":"2020-06-01","cited_by_count":88},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85},{"id":"2203.11205","title":"VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography","created":"2022-03-20","cited_by_count":84},{"id":"2202.12015","title":"Learning to Merge Tokens in Vision Transformers","created":"2022-02-24","cited_by_count":65},{"id":"2308.04657","title":"Which Tokens to Use? Investigating Token Reduction in Vision Transformers","created":"2023-08-09","cited_by_count":60},{"id":"1807.01477","title":"Diversity in Machine Learning","created":"2018-07-04","cited_by_count":48},{"id":"2211.11315","title":"Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers","created":"2022-11-21","cited_by_count":47},{"id":"2305.13689","title":"Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training","created":"2023-05-23","cited_by_count":39},{"id":"2106.02112","title":"Finding and Fixing Spurious Patterns with Explanations","created":"2021-06-03","cited_by_count":38},{"id":"2204.08945","title":"Missingness Bias in Model Debugging","created":"2022-04-19","cited_by_count":38},{"id":"2203.09125","title":"Are Vision Transformers Robust to Spurious Correlations?","created":"2022-03-17","cited_by_count":36},{"id":"2207.12020","title":"Domain-invariant Feature Exploration for Domain Generalization","created":"2022-07-25","cited_by_count":34},{"id":"2006.12009","title":"Feature Alignment and Restoration for Domain Generalization and Adaptation","created":"2020-06-22","cited_by_count":31},{"id":"2301.13293","title":"Overcoming Simplicity Bias in Deep Networks using a Feature Sieve","created":"2023-01-30","cited_by_count":29},{"id":"2203.15566","title":"Core Risk Minimization using Salient ImageNet","created":"2022-03-28","cited_by_count":15},{"id":"2211.14646","title":"Towards Improved Input Masking for Convolutional Neural Networks","created":"2022-11-26","cited_by_count":8},{"id":"2106.07141","title":"Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attacks","created":"2021-06-14","cited_by_count":6},{"id":"2401.02430","title":"Automated Classification of Model Errors on ImageNet","created":"2023-11-13","cited_by_count":6},{"id":"2111.11056","title":"Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes","created":"2021-11-22","cited_by_count":3}],"next_cursor":null}