{"list":"other","total":73,"rows":[{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"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":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"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":"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":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2011.03395","title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","created":"2020-11-06","cited_by_count":496},{"id":"1902.10178","title":"Unmasking Clever Hans Predictors and Assessing What Machines Really Learn","created":"2019-02-26","cited_by_count":365},{"id":"2006.09994","title":"Noise or Signal: The Role of Image Backgrounds in Object Recognition","created":"2020-06-17","cited_by_count":343},{"id":"2006.07159","title":"Are we done with ImageNet?","created":"2020-06-12","cited_by_count":333},{"id":"1506.02106","title":"What's the Point: Semantic Segmentation with Point Supervision","created":"2015-06-06","cited_by_count":298},{"id":"1703.03717","title":"Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations","created":"2017-03-10","cited_by_count":294},{"id":"1912.02315","title":"12-in-1: Multi-Task Vision and Language Representation Learning","created":"2019-12-05","cited_by_count":278},{"id":"1904.05044","title":"Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations","created":"2019-04-10","cited_by_count":247},{"id":"1908.07086","title":"Human uncertainty makes classification more robust","created":"2019-08-19","cited_by_count":235},{"id":"1912.03098","title":"Connecting Vision and Language with Localized Narratives","created":"2019-12-06","cited_by_count":226},{"id":"2109.04617","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","created":"2021-09-10","cited_by_count":222},{"id":"1910.02806","title":"Learning De-biased Representations with Biased Representations","created":"2019-10-07","cited_by_count":199},{"id":"1906.10169","title":"RUBi: Reducing Unimodal Biases in Visual Question Answering","created":"2019-06-24","cited_by_count":185},{"id":"1908.07898","title":"Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets","created":"2019-08-21","cited_by_count":175},{"id":"1603.08507","title":"Generating Visual Explanations","created":"2016-03-28","cited_by_count":158},{"id":"2001.07437","title":"Evaluating Weakly Supervised Object Localization Methods Right","created":"2020-01-21","cited_by_count":105},{"id":"2007.08558","title":"On Robustness and Transferability of Convolutional Neural Networks","created":"2020-07-16","cited_by_count":98},{"id":"1810.09957","title":"NSML: Meet the MLaaS platform with a real-world case study","created":"2018-10-08","cited_by_count":70},{"id":"2007.06661","title":"Robustness to Spurious Correlations via Human Annotations","created":"2020-07-13","cited_by_count":62},{"id":"2211.04533","title":"Harmonizing the object recognition strategies of deep neural networks with humans","created":"2022-11-08","cited_by_count":59},{"id":"1805.03818","title":"Training Classifiers with Natural Language Explanations","created":"2018-05-10","cited_by_count":58},{"id":"1705.08280","title":"How hard can it be? Estimating the difficulty of visual search in an image","created":"2017-05-23","cited_by_count":52},{"id":"1812.06707","title":"Not Using the Car to See the Sidewalk: Quantifying and Controlling the Effects of Context in Classification and Segmentation","created":"2018-12-17","cited_by_count":49},{"id":"2010.07891","title":"Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention","created":"2020-10-15","cited_by_count":45},{"id":"2206.01161","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","created":"2022-06-02","cited_by_count":41},{"id":"1912.07249","title":"Mimetics: Towards Understanding Human Actions Out of Context","created":"2019-12-16","cited_by_count":32},{"id":"2202.08926","title":"On Guiding Visual Attention with Language Specification","created":"2022-02-17","cited_by_count":30},{"id":"1805.11614","title":"Deep Learning under Privileged Information Using Heteroscedastic Dropout","created":"2018-05-29","cited_by_count":27},{"id":"2103.10415","title":"Refining Language Models with Compositional Explanations","created":"2021-03-18","cited_by_count":27},{"id":"2202.02838","title":"Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment","created":"2022-02-06","cited_by_count":27},{"id":"2010.10804","title":"UFO$^2$: A Unified Framework towards Omni-supervised Object Detection","created":"2020-10-21","cited_by_count":26},{"id":"1611.09309","title":"Gaze Embeddings for Zero-Shot Image Classification","created":"2016-11-28","cited_by_count":25},{"id":"2112.00071","title":"What to Learn, and How: Toward Effective Learning from Rationales","created":"2021-11-30","cited_by_count":25},{"id":"2210.14142","title":"From colouring-in to pointillism: revisiting semantic segmentation supervision","created":"2022-10-25","cited_by_count":22},{"id":"2111.01628","title":"Human Attention in Fine-grained Classification","created":"2021-11-02","cited_by_count":21},{"id":"1608.05203","title":"Seeing with Humans: Gaze-Assisted Neural Image Captioning","created":"2016-08-18","cited_by_count":20},{"id":"2104.08885","title":"A survey of image labelling for computer vision applications","created":"2021-04-18","cited_by_count":18},{"id":"2303.12641","title":"Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models","created":"2023-03-22","cited_by_count":17},{"id":"2011.04592","title":"Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze","created":"2020-11-09","cited_by_count":16},{"id":"2302.05721","title":"Synthesizing Human Gaze Feedback for Improved NLP Performance","created":"2023-02-11","cited_by_count":16},{"id":"2303.11932","title":"Studying How to Efficiently and Effectively Guide Models with Explanations","created":"2023-03-21","cited_by_count":16},{"id":"2105.05964","title":"Connecting What to Say With Where to Look by Modeling Human Attention Traces","created":"2021-05-12","cited_by_count":13},{"id":"1904.07478","title":"GradMask: Reduce Overfitting by Regularizing Saliency","created":"2019-04-16","cited_by_count":12},{"id":"1702.08681","title":"MIML-FCN+: Multi-instance Multi-label Learning via Fully Convolutional Networks with Privileged Information","created":"2017-02-28","cited_by_count":10},{"id":"1410.0389","title":"Learning to Transfer Privileged Information","created":"2014-10-01","cited_by_count":6},{"id":"1701.06772","title":"Training Group Orthogonal Neural Networks with Privileged Information","created":"2017-01-24","cited_by_count":6},{"id":"2211.07885","title":"Using Human Perception to Regularize Transfer Learning","created":"2022-11-15","cited_by_count":6}],"next_cursor":null}