{"list":"other","total":59,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"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":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"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":"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":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"id":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362},{"id":"2006.07159","title":"Are we done with ImageNet?","created":"2020-06-12","cited_by_count":333},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2106.05237","title":"Knowledge distillation: A good teacher is patient and consistent","created":"2021-06-09","cited_by_count":259},{"id":"2103.14586","title":"Understanding Robustness of Transformers for Image Classification","created":"2021-03-26","cited_by_count":249},{"id":"2010.15327","title":"Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth","created":"2020-10-29","cited_by_count":245},{"id":"2206.02770","title":"Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts","created":"2022-06-06","cited_by_count":203},{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190},{"id":"2003.11142","title":"BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models","created":"2020-03-24","cited_by_count":188},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184},{"id":"2106.09785","title":"Efficient Self-supervised Vision Transformers for Representation Learning","created":"2021-06-17","cited_by_count":149},{"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":"2204.08790","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","created":"2022-04-19","cited_by_count":141},{"id":"2106.02852","title":"Patch Slimming for Efficient Vision Transformers","created":"2021-06-05","cited_by_count":133},{"id":"2110.14739","title":"Generalized Shape Metrics on Neural Representations","created":"2021-10-27","cited_by_count":112},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98},{"id":"2205.01580","title":"Better plain ViT baselines for ImageNet-1k","created":"2022-05-03","cited_by_count":98},{"id":"2205.10337","title":"UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes","created":"2022-05-20","cited_by_count":78},{"id":"2104.08803","title":"Consistent Accelerated Inference via Confident Adaptive Transformers","created":"2021-04-18","cited_by_count":74},{"id":"1912.00998","title":"A Multigrid Method for Efficiently Training Video Models","created":"2019-12-02","cited_by_count":52},{"id":"2202.11921","title":"Auto-scaling Vision Transformers without Training","created":"2022-02-24","cited_by_count":15},{"id":"2205.11397","title":"Super Vision Transformer","created":"2022-05-23","cited_by_count":13}],"next_cursor":null}