{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"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":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"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":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1601.06759","title":"Pixel Recurrent Neural Networks","created":"2016-01-25","cited_by_count":816},{"id":"1606.04934","title":"Improving Variational Inference with Inverse Autoregressive Flow","created":"2016-06-15","cited_by_count":640},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"1608.04471","title":"Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm","created":"2016-08-16","cited_by_count":507},{"id":"1905.08094","title":"Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation","created":"2019-05-17","cited_by_count":497},{"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":"1511.02222","title":"Deep Kernel Learning","created":"2015-11-06","cited_by_count":445},{"id":"1807.01613","title":"Conditional Neural Processes","created":"2018-07-04","cited_by_count":426},{"id":"1805.10123","title":"TADAM: Task dependent adaptive metric for improved few-shot learning","created":"2018-05-23","cited_by_count":408},{"id":"1804.09458","title":"Dynamic Few-Shot Visual Learning without Forgetting","created":"2018-04-25","cited_by_count":385},{"id":"1907.09693","title":"A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection","created":"2019-07-23","cited_by_count":374},{"id":"1602.02282","title":"Ladder Variational Autoencoders","created":"2016-02-06","cited_by_count":318},{"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":"1807.01622","title":"Neural Processes","created":"2018-07-04","cited_by_count":311},{"id":"1901.05761","title":"Attentive Neural Processes","created":"2019-01-17","cited_by_count":283},{"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":"1707.04175","title":"Distral: Robust Multitask Reinforcement Learning","created":"2017-07-13","cited_by_count":233},{"id":"1611.05148","title":"Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering","created":"2016-11-16","cited_by_count":220},{"id":"1806.03836","title":"Bayesian Model-Agnostic Meta-Learning","created":"2018-06-11","cited_by_count":194},{"id":"1903.10145","title":"Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing","created":"2019-03-25","cited_by_count":191},{"id":"1611.02731","title":"Variational Lossy Autoencoder","created":"2016-11-08","cited_by_count":176},{"id":"1910.13556","title":"Convolutional Conditional Neural Processes","created":"2019-10-29","cited_by_count":142},{"id":"1801.03558","title":"Inference Suboptimality in Variational Autoencoders","created":"2018-01-10","cited_by_count":132},{"id":"1810.00825","title":"Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks","created":"2018-10-01","cited_by_count":132},{"id":"1906.07697","title":"Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes","created":"2019-06-18","cited_by_count":131},{"id":"1901.05534","title":"Lagging Inference Networks and Posterior Collapse in Variational Autoencoders","created":"2019-01-16","cited_by_count":124},{"id":"1706.03466","title":"Few-Shot Image Recognition by Predicting Parameters from Activations","created":"2017-06-12","cited_by_count":122},{"id":"1606.02185","title":"Towards a Neural Statistician","created":"2016-06-07","cited_by_count":121},{"id":"1805.10196","title":"Maximizing acquisition functions for Bayesian optimization","created":"2018-05-25","cited_by_count":114},{"id":"1805.09921","title":"Meta-Learning Probabilistic Inference For Prediction","created":"2018-05-24","cited_by_count":110},{"id":"1703.10631","title":"Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention","created":"2017-03-30","cited_by_count":107},{"id":"2001.08726","title":"Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning","created":"2020-01-23","cited_by_count":103},{"id":"1912.03820","title":"Meta-Learning without Memorization","created":"2019-12-09","cited_by_count":92},{"id":"1702.08139","title":"Improved Variational Autoencoders for Text Modeling using Dilated Convolutions","created":"2017-02-27","cited_by_count":81},{"id":"2102.12108","title":"The Promises and Pitfalls of Deep Kernel Learning","created":"2021-02-24","cited_by_count":81},{"id":"1904.13132","title":"A critical analysis of self-supervision, or what we can learn from a single image","created":"2019-04-30","cited_by_count":76},{"id":"2007.01332","title":"Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes","created":"2020-07-02","cited_by_count":76},{"id":"1905.05301","title":"Hierarchically Structured Meta-learning","created":"2019-05-13","cited_by_count":68},{"id":"2011.11819","title":"When Machine Learning Meets Privacy: A Survey and Outlook","created":"2020-11-24","cited_by_count":68},{"id":"1810.07218","title":"Incremental Few-Shot Learning with Attention Attractor Networks","created":"2018-10-16","cited_by_count":66},{"id":"1702.08658","title":"Towards Deeper Understanding of Variational Autoencoding Models","created":"2017-02-28","cited_by_count":56},{"id":"1906.10264","title":"Sequential Neural Processes","created":"2019-06-24","cited_by_count":55},{"id":"2003.12843","title":"A Close Look at Deep Learning with Small Data","created":"2020-03-28","cited_by_count":54},{"id":"1806.10166","title":"Modular meta-learning","created":"2018-06-26","cited_by_count":51},{"id":"1905.12917","title":"Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks","created":"2019-05-30","cited_by_count":48},{"id":"2101.02833","title":"Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition","created":"2021-01-08","cited_by_count":48},{"id":"1511.06348","title":"How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?","created":"2015-11-19","cited_by_count":45},{"id":"1605.06197","title":"Stick-Breaking Variational Autoencoders","created":"2016-05-20","cited_by_count":44},{"id":"1901.02739","title":"Dirichlet Variational Autoencoder","created":"2019-01-09","cited_by_count":43},{"id":"1906.08324","title":"The Functional Neural Process","created":"2019-06-19","cited_by_count":43},{"id":"2008.02956","title":"Bootstrapping Neural Processes","created":"2020-08-07","cited_by_count":40},{"id":"2010.07092","title":"Data Augmentation for Meta-Learning","created":"2020-10-14","cited_by_count":38},{"id":"1702.02390","title":"A Hybrid Convolutional Variational Autoencoder for Text Generation","created":"2017-02-08","cited_by_count":33},{"id":"1702.08396","title":"Learning Hierarchical Features from Generative Models","created":"2017-02-27","cited_by_count":27},{"id":"2010.11545","title":"Online Structured Meta-learning","created":"2020-10-22","cited_by_count":27},{"id":"2001.00745","title":"Automated Relational Meta-learning","created":"2020-01-03","cited_by_count":25},{"id":"1807.08919","title":"The Variational Homoencoder: Learning to learn high capacity generative models from few examples","created":"2018-07-24","cited_by_count":23},{"id":"2106.03195","title":"Meta-Learning Reliable Priors in the Function Space","created":"2021-06-06","cited_by_count":23},{"id":"1905.12131","title":"Adaptive Deep Kernel Learning","created":"2019-05-28","cited_by_count":15},{"id":"2103.16277","title":"Conditional Meta-Learning of Linear Representations","created":"2021-03-30","cited_by_count":12},{"id":"2009.03228","title":"Information Theoretic Meta Learning with Gaussian Processes","created":"2020-09-07","cited_by_count":11},{"id":"1402.0480","title":"Efficient Gradient-Based Inference through Transformations between Bayes Nets and Neural Nets","created":"2014-02-03","cited_by_count":5},{"id":"1812.07172","title":"Toward Multimodal Model-Agnostic Meta-Learning","created":"2018-12-18","cited_by_count":4}],"next_cursor":null}