{"list":"other","total":55,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"2104.07857","title":"ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning","created":"2021-04-16","cited_by_count":256},{"id":"1411.5908","title":"Understanding image representations by measuring their equivariance and equivalence","created":"2014-11-21","cited_by_count":243},{"id":"1609.01596","title":"Direct Feedback Alignment Provides Learning in Deep Neural Networks","created":"2016-09-06","cited_by_count":240},{"id":"2106.07682","title":"Revisiting Model Stitching to Compare Neural Representations","created":"2021-06-14","cited_by_count":209},{"id":"1412.7525","title":"Difference Target Propagation","created":"2014-12-23","cited_by_count":148},{"id":"2105.15075","title":"Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition","created":"2021-05-31","cited_by_count":144},{"id":"1608.05343","title":"Decoupled Neural Interfaces using Synthetic Gradients","created":"2016-08-18","cited_by_count":137},{"id":"2006.09503","title":"Memory-Efficient Pipeline-Parallel DNN Training","created":"2020-06-16","cited_by_count":134},{"id":"1812.11446","title":"Greedy Layerwise Learning Can Scale to ImageNet","created":"2018-12-29","cited_by_count":115},{"id":"2010.05300","title":"Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification","created":"2020-10-11","cited_by_count":100},{"id":"1407.7906","title":"How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation","created":"2014-07-29","cited_by_count":79},{"id":"1901.08164","title":"Decoupled Greedy Learning of CNNs","created":"2019-01-23","cited_by_count":78},{"id":"2110.14633","title":"Similarity and Matching of Neural Network Representations","created":"2021-10-27","cited_by_count":78},{"id":"2210.17409","title":"Deep Model Reassembly","created":"2022-10-24","cited_by_count":78},{"id":"2105.03245","title":"Adaptive Focus for Efficient Video Recognition","created":"2021-05-07","cited_by_count":77},{"id":"2101.10832","title":"Revisiting Locally Supervised Learning: an Alternative to End-to-end Training","created":"2021-01-26","cited_by_count":71},{"id":"1605.02026","title":"Training Neural Networks Without Gradients: A Scalable ADMM Approach","created":"2016-05-06","cited_by_count":61},{"id":"1411.0247","title":"Random feedback weights support learning in deep neural networks","created":"2014-11-02","cited_by_count":47},{"id":"2104.12753","title":"Vision Transformers with Patch Diversification","created":"2021-04-26","cited_by_count":45},{"id":"2209.08310","title":"Learning to Weight Samples for Dynamic Early-exiting Networks","created":"2022-09-17","cited_by_count":44},{"id":"2211.09703","title":"EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones","created":"2022-11-17","cited_by_count":43},{"id":"1804.10574","title":"Decoupled Parallel Backpropagation with Convergence Guarantee","created":"2018-04-27","cited_by_count":39},{"id":"1703.00522","title":"Understanding Synthetic Gradients and Decoupled Neural Interfaces","created":"2017-03-01","cited_by_count":35},{"id":"2106.06788","title":"Learngene: From Open-World to Your Learning Task","created":"2021-06-12","cited_by_count":27},{"id":"1711.07354","title":"Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks","created":"2017-11-20","cited_by_count":26},{"id":"2012.04915","title":"Progressive Network Grafting for Few-Shot Knowledge Distillation","created":"2020-12-09","cited_by_count":25},{"id":"2210.06223","title":"Latency-aware Spatial-wise Dynamic Networks","created":"2022-10-12","cited_by_count":25},{"id":"1805.01532","title":"Lifted Neural Networks","created":"2018-05-03","cited_by_count":20},{"id":"1811.01501","title":"Lifted Proximal Operator Machines","created":"2018-11-05","cited_by_count":14}],"next_cursor":null}