{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1912.01991","title":"Self-Supervised Learning of Pretext-Invariant Representations","created":"2019-12-04","cited_by_count":808},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2005.04966","title":"Prototypical Contrastive Learning of Unsupervised Representations","created":"2020-05-11","cited_by_count":640},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"2009.00236","title":"A Survey of Deep Active Learning","created":"2020-08-30","cited_by_count":554},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"1910.04867","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","created":"2019-10-01","cited_by_count":425},{"id":"2006.06882","title":"Rethinking Pre-training and Self-training","created":"2020-06-11","cited_by_count":352},{"id":"1608.05167","title":"AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification","created":"2016-08-18","cited_by_count":347},{"id":"1603.06668","title":"Learning Representations for Automatic Colorization","created":"2016-03-22","cited_by_count":251},{"id":"1503.01817","title":"YFCC100M: The New Data in Multimedia Research","created":"2015-03-05","cited_by_count":235},{"id":"1905.00546","title":"Billion-scale semi-supervised learning for image classification","created":"2019-05-02","cited_by_count":232},{"id":"1702.05693","title":"CityPersons: A Diverse Dataset for Pedestrian Detection","created":"2017-02-19","cited_by_count":172},{"id":"1912.07726","title":"Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy","created":"2019-12-16","cited_by_count":156},{"id":"1506.08959","title":"A Large-Scale Car Dataset for Fine-Grained Categorization and Verification","created":"2015-06-30","cited_by_count":130},{"id":"2107.14263","title":"Batch Active Learning at Scale","created":"2021-07-29","cited_by_count":127},{"id":"2101.05022","title":"Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels","created":"2021-01-13","cited_by_count":118},{"id":"2108.11353","title":"Multi-Task Self-Training for Learning General Representations","created":"2021-08-25","cited_by_count":85},{"id":"2103.06191","title":"A Study of Face Obfuscation in ImageNet","created":"2021-03-10","cited_by_count":83},{"id":"2105.03494","title":"The iWildCam 2021 Competition Dataset","created":"2021-05-07","cited_by_count":77},{"id":"1610.02055","title":"Places: An Image Database for Deep Scene Understanding","created":"2016-10-06","cited_by_count":76},{"id":"2004.04699","title":"Scalable Active Learning for Object Detection","created":"2020-04-09","cited_by_count":58},{"id":"2107.14153","title":"Semi-Supervised Active Learning with Temporal Output Discrepancy","created":"2021-07-29","cited_by_count":50},{"id":"1907.06167","title":"FoodX-251: A Dataset for Fine-grained Food Classification","created":"2019-07-14","cited_by_count":33},{"id":"2103.10107","title":"Danish Fungi 2020 -- Not Just Another Image Recognition Dataset","created":"2021-03-18","cited_by_count":27},{"id":"2108.05887","title":"Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations","created":"2021-08-12","cited_by_count":24},{"id":"2107.13098","title":"A Tale Of Two Long Tails","created":"2021-07-27","cited_by_count":19},{"id":"2105.11653","title":"Scaling Hierarchical Agglomerative Clustering to Billion-sized Datasets","created":"2021-05-25","cited_by_count":11}],"next_cursor":null}