{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"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":"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"1907.09682","title":"Similarity-Preserving Knowledge Distillation","created":"2019-07-23","cited_by_count":516},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"1904.05835","title":"Variational Information Distillation for Knowledge Transfer","created":"2019-04-11","cited_by_count":324},{"id":"2208.06366","title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers","created":"2022-08-12","cited_by_count":303},{"id":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297},{"id":"2104.09044","title":"Distilling Knowledge via Knowledge Review","created":"2021-04-19","cited_by_count":288},{"id":"1904.01802","title":"Correlation Congruence for Knowledge Distillation","created":"2019-04-03","cited_by_count":285},{"id":"2012.15828","title":"MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers","created":"2020-12-31","cited_by_count":245},{"id":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234},{"id":"2011.13256","title":"Channel-wise Knowledge Distillation for Dense Prediction","created":"2020-11-26","cited_by_count":163},{"id":"2204.12997","title":"DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers","created":"2022-04-27","cited_by_count":65},{"id":"2208.04164","title":"Understanding Masked Image Modeling via Learning Occlusion Invariant Feature","created":"2022-08-08","cited_by_count":50},{"id":"1905.05901","title":"Learning What and Where to Transfer","created":"2019-05-15","cited_by_count":43},{"id":"2111.00674","title":"Distilling Object Detectors with Feature Richness","created":"2021-11-01","cited_by_count":38},{"id":"2208.12256","title":"Masked Autoencoders Enable Efficient Knowledge Distillers","created":"2022-08-25","cited_by_count":36},{"id":"2209.02432","title":"ViTKD: Practical Guidelines for ViT feature knowledge distillation","created":"2022-09-06","cited_by_count":34},{"id":"2202.07940","title":"Meta Knowledge Distillation","created":"2022-02-16","cited_by_count":20},{"id":"2205.09613","title":"Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection","created":"2022-05-19","cited_by_count":9},{"id":"2208.10139","title":"Rethinking Knowledge Distillation via Cross-Entropy","created":"2022-08-22","cited_by_count":9}],"next_cursor":null}