{"list":"other","total":258,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"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":"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":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"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":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"1904.04232","title":"A Closer Look at Few-shot Classification","created":"2019-04-08","cited_by_count":684},{"id":"1902.03368","title":"Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)","created":"2019-02-09","cited_by_count":669},{"id":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"1612.03242","title":"StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2016-12-10","cited_by_count":577},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1809.09401","title":"Hypergraph Neural Networks","created":"2018-09-25","cited_by_count":488},{"id":"1807.05960","title":"Meta-Learning with Latent Embedding Optimization","created":"2018-07-16","cited_by_count":476},{"id":"1904.05046","title":"Generalizing from a Few Examples: A Survey on Few-Shot Learning","created":"2019-04-10","cited_by_count":463},{"id":"1803.00676","title":"Meta-Learning for Semi-Supervised Few-Shot Classification","created":"2018-03-02","cited_by_count":456},{"id":"1908.06391","title":"PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment","created":"2019-08-18","cited_by_count":449},{"id":"2003.11539","title":"Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?","created":"2020-03-25","cited_by_count":437},{"id":"1412.6622","title":"Deep metric learning using Triplet network","created":"2014-12-20","cited_by_count":422},{"id":"2001.00326","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","created":"2020-01-02","cited_by_count":416},{"id":"1707.09835","title":"Meta-SGD: Learning to Learn Quickly for Few-Shot Learning","created":"2017-07-31","cited_by_count":379},{"id":"1909.09157","title":"Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML","created":"2019-09-19","cited_by_count":359},{"id":"1709.03410","title":"One-Shot Learning for Semantic Segmentation","created":"2017-09-11","cited_by_count":337},{"id":"1711.04043","title":"Few-Shot Learning with Graph Neural Networks","created":"2017-11-10","cited_by_count":324},{"id":"1909.03193","title":"KG-BERT: BERT for Knowledge Graph Completion","created":"2019-09-07","cited_by_count":324},{"id":"2003.08505","title":"A Metric Learning Reality Check","created":"2020-03-18","cited_by_count":321},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"1903.03096","title":"Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples","created":"2019-03-07","cited_by_count":315},{"id":"1909.02729","title":"A Baseline for Few-Shot Image Classification","created":"2019-09-06","cited_by_count":298},{"id":"1812.03664","title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","created":"2018-12-10","cited_by_count":294},{"id":"2104.05240","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","created":"2021-04-12","cited_by_count":291},{"id":"2003.06957","title":"Frustratingly Simple Few-Shot Object Detection","created":"2020-03-16","cited_by_count":282},{"id":"2008.01449","title":"Prior Guided Feature Enrichment Network for Few-Shot Segmentation","created":"2020-08-04","cited_by_count":271},{"id":"1712.00981","title":"Feature Generating Networks for Zero-Shot Learning","created":"2017-12-04","cited_by_count":257},{"id":"1806.02817","title":"Probabilistic Model-Agnostic Meta-Learning","created":"2018-06-07","cited_by_count":256},{"id":"1810.03548","title":"Meta-Learning: A Survey","created":"2018-10-08","cited_by_count":256},{"id":"2006.05987","title":"Revisiting Few-sample BERT Fine-tuning","created":"2020-06-10","cited_by_count":238},{"id":"2109.04332","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","created":"2021-09-09","cited_by_count":232},{"id":"1604.03169","title":"Using Deep Learning for Image-Based Plant Disease Detection","created":"2016-04-11","cited_by_count":219},{"id":"1910.07677","title":"Cross Attention Network for Few-shot Classification","created":"2019-10-17","cited_by_count":219},{"id":"1903.02351","title":"CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning","created":"2019-03-06","cited_by_count":217},{"id":"1910.08348","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","created":"2019-10-18","cited_by_count":217},{"id":"1812.01784","title":"Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders","created":"2018-12-05","cited_by_count":206},{"id":"1806.03836","title":"Bayesian Model-Agnostic Meta-Learning","created":"2018-06-11","cited_by_count":194},{"id":"2104.01538","title":"Hypercorrelation Squeeze for Few-Shot Segmentation","created":"2021-04-04","cited_by_count":193},{"id":"2008.03898","title":"Prototype Mixture Models for Few-shot Semantic Segmentation","created":"2020-08-10","cited_by_count":190},{"id":"1909.13140","title":"Feature Weighting and Boosting for Few-Shot Segmentation","created":"2019-09-28","cited_by_count":189},{"id":"2001.08735","title":"Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation","created":"2020-01-23","cited_by_count":185},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"1605.05395","title":"Learning Deep Representations of Fine-grained Visual Descriptions","created":"2016-05-17","cited_by_count":182},{"id":"1909.13032","title":"Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning","created":"2019-09-28","cited_by_count":182},{"id":"1801.08930","title":"Recasting Gradient-Based Meta-Learning as Hierarchical Bayes","created":"2018-01-26","cited_by_count":180},{"id":"2003.04390","title":"Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning","created":"2020-03-09","cited_by_count":179},{"id":"2007.11498","title":"CrossTransformers: spatially-aware few-shot transfer","created":"2020-07-22","cited_by_count":174},{"id":"1704.01719","title":"Beyond triplet loss: a deep quadruplet network for person re-identification","created":"2017-04-06","cited_by_count":172},{"id":"1810.09091","title":"SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation","created":"2018-10-22","cited_by_count":169},{"id":"2103.05950","title":"FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding","created":"2021-03-10","cited_by_count":168},{"id":"2101.06395","title":"Free Lunch for Few-shot Learning: Distribution Calibration","created":"2021-01-16","cited_by_count":165},{"id":"2007.06309","title":"Part-aware Prototype Network for Few-shot Semantic Segmentation","created":"2020-07-13","cited_by_count":162},{"id":"2106.01760","title":"Template-Based Named Entity Recognition Using BART","created":"2021-06-03","cited_by_count":153},{"id":"1805.07722","title":"Task-Agnostic Meta-Learning for Few-shot Learning","created":"2018-05-20","cited_by_count":151}],"next_cursor":"100"}