{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"2111.11426","title":"Neural Fields in Visual Computing and Beyond","created":"2021-11-22","cited_by_count":540},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"2006.07159","title":"Are we done with ImageNet?","created":"2020-06-12","cited_by_count":333},{"id":"2003.09871","title":"COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Images","created":"2020-03-22","cited_by_count":264},{"id":"2107.00645","title":"Global Filter Networks for Image Classification","created":"2021-07-01","cited_by_count":260},{"id":"1904.05044","title":"Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations","created":"2019-04-10","cited_by_count":247},{"id":"1505.00855","title":"Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature","created":"2015-05-05","cited_by_count":182},{"id":"1901.07973","title":"DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images","created":"2019-01-23","cited_by_count":134},{"id":"2103.07976","title":"TransFG: A Transformer Architecture for Fine-grained Recognition","created":"2021-03-14","cited_by_count":132},{"id":"2103.14862","title":"TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization","created":"2021-03-27","cited_by_count":123},{"id":"2001.07437","title":"Evaluating Weakly Supervised Object Localization Methods Right","created":"2020-01-21","cited_by_count":105},{"id":"2003.03836","title":"Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches","created":"2020-03-08","cited_by_count":92},{"id":"2002.10191","title":"Learning Attentive Pairwise Interaction for Fine-Grained Classification","created":"2020-02-24","cited_by_count":84},{"id":"2205.02151","title":"Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification","created":"2022-05-04","cited_by_count":78},{"id":"1903.02827","title":"Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up","created":"2019-03-07","cited_by_count":66},{"id":"2204.14244","title":"CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification","created":"2022-04-29","cited_by_count":65},{"id":"1909.04412","title":"Cross-X Learning for Fine-Grained Visual Categorization","created":"2019-09-10","cited_by_count":61},{"id":"2111.12294","title":"An Image Patch is a Wave: Phase-Aware Vision MLP","created":"2021-11-24","cited_by_count":61},{"id":"2204.03206","title":"L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation","created":"2022-04-07","cited_by_count":57},{"id":"2008.05096","title":"Inter-Image Communication for Weakly Supervised Localization","created":"2020-08-12","cited_by_count":52},{"id":"1909.11378","title":"Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization","created":"2019-09-25","cited_by_count":51},{"id":"1805.07549","title":"Disc-aware Ensemble Network for Glaucoma Screening from Fundus Image","created":"2018-05-19","cited_by_count":39},{"id":"2101.11253","title":"Puzzle-CAM: Improved localization via matching partial and full features","created":"2021-01-27","cited_by_count":37},{"id":"1706.06969","title":"Comparing deep neural networks against humans: object recognition when the signal gets weaker","created":"2017-06-21","cited_by_count":34},{"id":"2107.08192","title":"RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition","created":"2021-07-17","cited_by_count":34},{"id":"2204.00220","title":"Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization","created":"2022-04-01","cited_by_count":25},{"id":"2112.05291","title":"LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization","created":"2021-12-10","cited_by_count":24},{"id":"2207.10447","title":"Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration","created":"2022-07-21","cited_by_count":20},{"id":"2004.02684","title":"Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition","created":"2020-04-06","cited_by_count":15},{"id":"2203.03937","title":"Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention","created":"2022-03-08","cited_by_count":14},{"id":"2005.14284","title":"Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning","created":"2020-05-28","cited_by_count":11},{"id":"2105.11852","title":"GCNBoost: Artwork Classification by Label Propagation through a Knowledge Graph","created":"2021-05-25","cited_by_count":11},{"id":"1906.00901","title":"The iMet Collection 2019 Challenge Dataset","created":"2019-06-03","cited_by_count":10},{"id":"2206.05763","title":"SeATrans: Learning Segmentation-Assisted diagnosis model via Transformer","created":"2022-06-12","cited_by_count":8}],"next_cursor":null}