{"list":"other","total":52,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"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":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"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":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"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":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1607.01759","title":"Bag of Tricks for Efficient Text Classification","created":"2016-07-06","cited_by_count":876},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"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":"1310.1531","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","created":"2013-10-06","cited_by_count":424},{"id":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"2110.01963","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","created":"2021-10-05","cited_by_count":327},{"id":"1403.6382","title":"CNN Features off-the-shelf: an Astounding Baseline for Recognition","created":"2014-03-23","cited_by_count":316},{"id":"2106.04156","title":"Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss","created":"2021-06-08","cited_by_count":313},{"id":"2011.13377","title":"How Well Do Self-Supervised Models Transfer?","created":"2020-11-26","cited_by_count":213},{"id":"2010.07922","title":"Representation Learning via Invariant Causal Mechanisms","created":"2020-10-15","cited_by_count":199},{"id":"1608.08614","title":"What makes ImageNet good for transfer learning?","created":"2016-08-30","cited_by_count":192},{"id":"2002.07017","title":"Learning Robust Representations via Multi-View Information Bottleneck","created":"2020-02-17","cited_by_count":191},{"id":"2205.01397","title":"Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)","created":"2022-05-03","cited_by_count":138},{"id":"1405.3531","title":"Return of the Devil in the Details: Delving Deep into Convolutional Nets","created":"2014-05-14","cited_by_count":122},{"id":"2105.05837","title":"When Does Contrastive Visual Representation Learning Work?","created":"2021-05-12","cited_by_count":92},{"id":"2105.08054","title":"Divide and Contrast: Self-supervised Learning from Uncurated Data","created":"2021-05-17","cited_by_count":85},{"id":"2005.13149","title":"On Mutual Information in Contrastive Learning for Visual Representations","created":"2020-05-27","cited_by_count":54},{"id":"2010.14766","title":"A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation","created":"2020-10-27","cited_by_count":52},{"id":"2106.10800","title":"Lossy Compression for Lossless Prediction","created":"2021-06-21","cited_by_count":52},{"id":"2201.00057","title":"Optimal Representations for Covariate Shift","created":"2021-12-31","cited_by_count":51},{"id":"1407.1610","title":"Analyzing the Performance of Multilayer Neural Networks for Object Recognition","created":"2014-07-07","cited_by_count":29},{"id":"2104.08313","title":"Does language help generalization in vision models?","created":"2021-04-16","cited_by_count":19},{"id":"2012.11696","title":"Image Captioning as an Assistive Technology: Lessons Learned from VizWiz 2020 Challenge","created":"2020-12-21","cited_by_count":17}],"next_cursor":null}