{"list":"other","total":52,"rows":[{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1904.04232","title":"A Closer Look at Few-shot Classification","created":"2019-04-08","cited_by_count":684},{"id":"1807.05960","title":"Meta-Learning with Latent Embedding Optimization","created":"2018-07-16","cited_by_count":476},{"id":"1904.03758","title":"Meta-Learning with Differentiable Convex Optimization","created":"2019-04-07","cited_by_count":461},{"id":"1803.00676","title":"Meta-Learning for Semi-Supervised Few-Shot Classification","created":"2018-03-02","cited_by_count":456},{"id":"1412.1193","title":"New insights and perspectives on the natural gradient method","created":"2014-12-03","cited_by_count":443},{"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":"1805.10123","title":"TADAM: Task dependent adaptive metric for improved few-shot learning","created":"2018-05-23","cited_by_count":408},{"id":"1805.08136","title":"Meta-learning with differentiable closed-form solvers","created":"2018-05-21","cited_by_count":397},{"id":"1804.09458","title":"Dynamic Few-Shot Visual Learning without Forgetting","created":"2018-04-25","cited_by_count":385},{"id":"1909.09157","title":"Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML","created":"2019-09-19","cited_by_count":359},{"id":"1711.04043","title":"Few-Shot Learning with Graph Neural Networks","created":"2017-11-10","cited_by_count":324},{"id":"1707.09564","title":"A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks","created":"2017-07-29","cited_by_count":314},{"id":"1810.09502","title":"How to train your MAML","created":"2018-10-22","cited_by_count":309},{"id":"1812.02391","title":"Meta-Transfer Learning for Few-Shot Learning","created":"2018-12-06","cited_by_count":306},{"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":"1806.02817","title":"Probabilistic Model-Agnostic Meta-Learning","created":"2018-06-07","cited_by_count":256},{"id":"1806.03836","title":"Bayesian Model-Agnostic Meta-Learning","created":"2018-06-11","cited_by_count":194},{"id":"1801.08930","title":"Recasting Gradient-Based Meta-Learning as Hierarchical Bayes","created":"2018-01-26","cited_by_count":180},{"id":"1907.12087","title":"Charting the Right Manifold: Manifold Mixup for Few-shot Learning","created":"2019-07-28","cited_by_count":136},{"id":"1302.4245","title":"Gaussian Process Kernels for Pattern Discovery and Extrapolation","created":"2013-02-18","cited_by_count":132},{"id":"1706.03466","title":"Few-Shot Image Recognition by Predicting Parameters from Activations","created":"2017-06-12","cited_by_count":122},{"id":"2009.13000","title":"Interventional Few-Shot Learning","created":"2020-09-28","cited_by_count":112},{"id":"1306.2119","title":"Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)","created":"2013-06-10","cited_by_count":111},{"id":"1805.09921","title":"Meta-Learning Probabilistic Inference For Prediction","created":"2018-05-24","cited_by_count":110},{"id":"1909.00025","title":"Meta-Learning with Warped Gradient Descent","created":"2019-08-30","cited_by_count":98},{"id":"1905.06549","title":"TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning","created":"2019-05-16","cited_by_count":91},{"id":"1902.00744","title":"Asymmetric Valleys: Beyond Sharp and Flat Local Minima","created":"2019-02-02","cited_by_count":90},{"id":"1806.05594","title":"There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average","created":"2018-06-14","cited_by_count":82},{"id":"2005.11879","title":"Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks","created":"2020-05-25","cited_by_count":77},{"id":"1902.03356","title":"Meta-Curvature","created":"2019-02-09","cited_by_count":70},{"id":"1903.11341","title":"Diversity with Cooperation: Ensemble Methods for Few-Shot Classification","created":"2019-03-27","cited_by_count":70},{"id":"1910.02224","title":"Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning","created":"2019-10-05","cited_by_count":67},{"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":"1807.08912","title":"Meta-Learning Priors for Efficient Online Bayesian Regression","created":"2018-07-24","cited_by_count":48},{"id":"2004.12696","title":"Empirical Bayes Transductive Meta-Learning with Synthetic Gradients","created":"2020-04-27","cited_by_count":48},{"id":"2002.06753","title":"Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks","created":"2020-02-17","cited_by_count":47},{"id":"1906.04659","title":"Stable Rank Normalization for Improved Generalization in Neural Networks and GANs","created":"2019-06-11","cited_by_count":41},{"id":"1912.02738","title":"MetaFun: Meta-Learning with Iterative Functional Updates","created":"2019-12-05","cited_by_count":34},{"id":"2007.10417","title":"Bayesian Few-Shot Classification with One-vs-Each P\\'olya-Gamma Augmented Gaussian Processes","created":"2020-07-20","cited_by_count":32},{"id":"2003.08561","title":"XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning","created":"2020-03-19","cited_by_count":31},{"id":"2106.15615","title":"A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning","created":"2021-06-29","cited_by_count":12}],"next_cursor":null}