{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"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":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1904.04232","title":"A Closer Look at Few-shot Classification","created":"2019-04-08","cited_by_count":684},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"1807.05960","title":"Meta-Learning with Latent Embedding Optimization","created":"2018-07-16","cited_by_count":476},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"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":"2003.11539","title":"Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?","created":"2020-03-25","cited_by_count":437},{"id":"1912.08795","title":"Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion","created":"2019-12-18","cited_by_count":423},{"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":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1711.04043","title":"Few-Shot Learning with Graph Neural Networks","created":"2017-11-10","cited_by_count":324},{"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":"1812.02391","title":"Meta-Transfer Learning for Few-Shot Learning","created":"2018-12-06","cited_by_count":306},{"id":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"1603.04779","title":"Revisiting Batch Normalization For Practical Domain Adaptation","created":"2016-03-15","cited_by_count":288},{"id":"1810.12890","title":"DropBlock: A regularization method for convolutional networks","created":"2018-10-30","cited_by_count":262},{"id":"1902.00113","title":"Episodic Training for Domain Generalization","created":"2019-01-31","cited_by_count":245},{"id":"1910.07677","title":"Cross Attention Network for Few-shot Classification","created":"2019-10-17","cited_by_count":219},{"id":"2001.08735","title":"Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation","created":"2020-01-23","cited_by_count":185},{"id":"2003.12060","title":"Negative Margin Matters: Understanding Margin in Few-shot Classification","created":"2020-03-26","cited_by_count":129},{"id":"2104.00946","title":"UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles","created":"2021-04-02","cited_by_count":96},{"id":"1907.04829","title":"BAM! Born-Again Multi-Task Networks for Natural Language Understanding","created":"2019-07-10","cited_by_count":85},{"id":"2103.16765","title":"Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation","created":"2021-03-31","cited_by_count":83},{"id":"1905.01102","title":"Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning","created":"2019-05-03","cited_by_count":69},{"id":"2007.08790","title":"Explanation-Guided Training for Cross-Domain Few-Shot Classification","created":"2020-07-17","cited_by_count":58},{"id":"1903.05050","title":"Dense Classification and Implanting for Few-Shot Learning","created":"2019-03-12","cited_by_count":56},{"id":"2103.12562","title":"Transferable Semantic Augmentation for Domain Adaptation","created":"2021-03-23","cited_by_count":56},{"id":"1805.05551","title":"Knowledge Distillation in Generations: More Tolerant Teachers Educate Better Students","created":"2018-05-15","cited_by_count":50},{"id":"2205.03805","title":"A Closer Look at Few-shot Image Generation","created":"2022-05-08","cited_by_count":49},{"id":"2002.06753","title":"Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks","created":"2020-02-17","cited_by_count":47},{"id":"1802.04376","title":"Few-Shot Learning with Metric-Agnostic Conditional Embeddings","created":"2018-02-12","cited_by_count":40},{"id":"2003.08626","title":"Domain-Adaptive Few-Shot Learning","created":"2020-03-19","cited_by_count":40},{"id":"2003.11132","title":"Born-Again Tree Ensembles","created":"2020-03-24","cited_by_count":38},{"id":"1811.05072","title":"Private Model Compression via Knowledge Distillation","created":"2018-11-13","cited_by_count":37},{"id":"2206.14532","title":"Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?","created":"2022-06-29","cited_by_count":32},{"id":"2110.14202","title":"Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning","created":"2021-10-27","cited_by_count":22},{"id":"2004.02034","title":"Optimization of Image Embeddings for Few Shot Learning","created":"2020-04-04","cited_by_count":6}],"next_cursor":null}