{"list":"other","total":64,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1904.04232","title":"A Closer Look at Few-shot Classification","created":"2019-04-08","cited_by_count":684},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"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":"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":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361},{"id":"2107.00645","title":"Global Filter Networks for Image Classification","created":"2021-07-01","cited_by_count":260},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","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":"2011.10881","title":"Rethinking Transformer-based Set Prediction for Object Detection","created":"2020-11-21","cited_by_count":156},{"id":"1805.07722","title":"Task-Agnostic Meta-Learning for Few-shot Learning","created":"2018-05-20","cited_by_count":151},{"id":"2104.10858","title":"All Tokens Matter: Token Labeling for Training Better Vision Transformers","created":"2021-04-22","cited_by_count":144},{"id":"1906.05186","title":"Boosting Few-Shot Visual Learning with Self-Supervision","created":"2019-06-12","cited_by_count":140},{"id":"1907.12087","title":"Charting the Right Manifold: Manifold Mixup for Few-shot Learning","created":"2019-07-28","cited_by_count":136},{"id":"2006.04868","title":"DoubleU-Net: A Deep Convolutional Neural Network for Medical Image Segmentation","created":"2020-06-08","cited_by_count":125},{"id":"2102.12627","title":"How to represent part-whole hierarchies in a neural network","created":"2021-02-25","cited_by_count":123},{"id":"1706.03466","title":"Few-Shot Image Recognition by Predicting Parameters from Activations","created":"2017-06-12","cited_by_count":122},{"id":"1905.01436","title":"Edge-labeling Graph Neural Network for Few-shot Learning","created":"2019-05-04","cited_by_count":114},{"id":"2103.10619","title":"Scalable Vision Transformers with Hierarchical Pooling","created":"2021-03-19","cited_by_count":84},{"id":"2108.09666","title":"Relational Embedding for Few-Shot Classification","created":"2021-08-22","cited_by_count":74},{"id":"2110.03860","title":"Token Pooling in Vision Transformers","created":"2021-10-08","cited_by_count":69},{"id":"2106.02351","title":"SOLQ: Segmenting Objects by Learning Queries","created":"2021-06-04","cited_by_count":68},{"id":"2103.01315","title":"Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning","created":"2021-03-01","cited_by_count":56},{"id":"2104.07841","title":"Pareto Self-Supervised Training for Few-Shot Learning","created":"2021-04-16","cited_by_count":52},{"id":"2110.03909","title":"Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning","created":"2021-10-08","cited_by_count":49},{"id":"2101.02833","title":"Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition","created":"2021-01-08","cited_by_count":48},{"id":"2108.01684","title":"Vision Transformer with Progressive Sampling","created":"2021-08-03","cited_by_count":44},{"id":"2108.06747","title":"SOTR: Segmenting Objects with Transformers","created":"2021-08-15","cited_by_count":42},{"id":"2103.13582","title":"Learning Dynamic Alignment via Meta-filter for Few-shot Learning","created":"2021-03-25","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":"2109.07607","title":"Partner-Assisted Learning for Few-Shot Image Classification","created":"2021-09-15","cited_by_count":36},{"id":"1904.08502","title":"Few-Shot Learning with Localization in Realistic Settings","created":"2019-04-09","cited_by_count":34},{"id":"1909.04332","title":"PARN: Position-Aware Relation Networks for Few-Shot Learning","created":"2019-09-10","cited_by_count":27},{"id":"2108.12104","title":"Binocular Mutual Learning for Improving Few-shot Classification","created":"2021-08-27","cited_by_count":26},{"id":"2108.00580","title":"GraphFPN: Graph Feature Pyramid Network for Object Detection","created":"2021-08-02","cited_by_count":25},{"id":"2011.11872","title":"Mixture-based Feature Space Learning for Few-shot Image Classification","created":"2020-11-24","cited_by_count":23},{"id":"2108.03428","title":"PSViT: Better Vision Transformer via Token Pooling and Attention Sharing","created":"2021-08-07","cited_by_count":21},{"id":"2109.05749","title":"Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning","created":"2021-09-13","cited_by_count":19},{"id":"2010.12084","title":"Few-shot Image Recognition with Manifolds","created":"2020-10-22","cited_by_count":2}],"next_cursor":null}