{"list":"other","total":56,"rows":[{"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2005.04966","title":"Prototypical Contrastive Learning of Unsupervised Representations","created":"2020-05-11","cited_by_count":640},{"id":"1807.05960","title":"Meta-Learning with Latent Embedding Optimization","created":"2018-07-16","cited_by_count":476},{"id":"1803.00676","title":"Meta-Learning for Semi-Supervised Few-Shot Classification","created":"2018-03-02","cited_by_count":456},{"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":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"1711.04043","title":"Few-Shot Learning with Graph Neural Networks","created":"2017-11-10","cited_by_count":324},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"1906.03158","title":"Matching the Blanks: Distributional Similarity for Relation Learning","created":"2019-06-07","cited_by_count":272},{"id":"1703.00837","title":"Meta Networks","created":"2017-03-02","cited_by_count":269},{"id":"1810.10147","title":"FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation","created":"2018-10-24","cited_by_count":254},{"id":"1911.04623","title":"SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning","created":"2019-11-12","cited_by_count":195},{"id":"2108.02035","title":"Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification","created":"2021-08-04","cited_by_count":183},{"id":"2003.04390","title":"Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning","created":"2020-03-09","cited_by_count":179},{"id":"2101.06395","title":"Free Lunch for Few-shot Learning: Distribution Calibration","created":"2021-01-16","cited_by_count":165},{"id":"2105.07464","title":"Few-NERD: A Few-Shot Named Entity Recognition Dataset","created":"2021-05-16","cited_by_count":152},{"id":"1904.11227","title":"Transferrable Prototypical Networks for Unsupervised Domain Adaptation","created":"2019-04-25","cited_by_count":141},{"id":"1907.12087","title":"Charting the Right Manifold: Manifold Mixup for Few-shot Learning","created":"2019-07-28","cited_by_count":136},{"id":"1706.03466","title":"Few-Shot Image Recognition by Predicting Parameters from Activations","created":"2017-06-12","cited_by_count":122},{"id":"2012.01506","title":"Few-Shot Classification with Feature Map Reconstruction Networks","created":"2020-12-02","cited_by_count":116},{"id":"1902.04552","title":"Infinite Mixture Prototypes for Few-Shot Learning","created":"2019-02-12","cited_by_count":99},{"id":"1910.07124","title":"FewRel 2.0: Towards More Challenging Few-Shot Relation Classification","created":"2019-10-16","cited_by_count":94},{"id":"1901.10514","title":"Hyperspherical Prototype Networks","created":"2019-01-29","cited_by_count":86},{"id":"2005.13826","title":"Boosting Few-Shot Learning With Adaptive Margin Loss","created":"2020-05-28","cited_by_count":83},{"id":"2010.01923","title":"Learning from Context or Names? An Empirical Study on Neural Relation Extraction","created":"2020-10-05","cited_by_count":75},{"id":"2109.07589","title":"CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning","created":"2021-09-15","cited_by_count":64},{"id":"2108.10604","title":"Prompt-Learning for Fine-Grained Entity Typing","created":"2021-08-24","cited_by_count":62},{"id":"1905.04398","title":"Few-Shot Learning with Embedded Class Models and Shot-Free Meta Training","created":"2019-05-10","cited_by_count":57},{"id":"2203.09770","title":"Prototypical Verbalizer for Prompt-based Few-shot Tuning","created":"2022-03-18","cited_by_count":53},{"id":"2204.04567","title":"Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification","created":"2022-04-09","cited_by_count":50},{"id":"2012.09831","title":"On Episodes, Prototypical Networks, and Few-shot Learning","created":"2020-12-17","cited_by_count":46},{"id":"2012.14978","title":"Few-Shot Named Entity Recognition: A Comprehensive Study","created":"2020-12-29","cited_by_count":41},{"id":"2106.14472","title":"Hyperbolic Busemann Learning with Ideal Prototypes","created":"2021-06-28","cited_by_count":41},{"id":"2007.02387","title":"Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs","created":"2020-07-05","cited_by_count":39},{"id":"1904.08502","title":"Few-Shot Learning with Localization in Realistic Settings","created":"2019-04-09","cited_by_count":34},{"id":"2103.11647","title":"Prototypical Representation Learning for Relation Extraction","created":"2021-03-22","cited_by_count":33},{"id":"1906.06678","title":"Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification","created":"2019-06-16","cited_by_count":32},{"id":"2109.13023","title":"An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labeling","created":"2021-09-27","cited_by_count":26},{"id":"2109.05473","title":"Exploring Task Difficulty for Few-Shot Relation Extraction","created":"2021-09-12","cited_by_count":24},{"id":"1912.04973","title":"A Two-Stage Approach to Few-Shot Learning for Image Recognition","created":"2019-12-10","cited_by_count":18},{"id":"2002.00153","title":"Asymmetric Distribution Measure for Few-shot Learning","created":"2020-02-01","cited_by_count":18},{"id":"2201.11576","title":"Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation","created":"2022-01-27","cited_by_count":8},{"id":"2210.13733","title":"Better Few-Shot Relation Extraction with Label Prompt Dropout","created":"2022-10-25","cited_by_count":8},{"id":"2010.07744","title":"A Theory of Hyperbolic Prototype Learning","created":"2020-10-15","cited_by_count":3},{"id":"1901.03860","title":"Prototypical Metric Transfer Learning for Continuous Speech Keyword Spotting With Limited Training Data","created":"2019-01-12","cited_by_count":1}],"next_cursor":null}