{"list":"other","total":69,"rows":[{"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":"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"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":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"2002.07394","title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","created":"2020-02-18","cited_by_count":692},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"1812.01187","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","created":"2018-12-04","cited_by_count":431},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281},{"id":"1708.02862","title":"WebVision Database: Visual Learning and Understanding from Web Data","created":"2017-08-09","cited_by_count":262},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207},{"id":"2105.07581","title":"Vision Transformers are Robust Learners","created":"2021-05-17","cited_by_count":207},{"id":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187},{"id":"2204.03645","title":"DaViT: Dual Attention Vision Transformers","created":"2022-04-07","cited_by_count":175},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155},{"id":"2104.10858","title":"All Tokens Matter: Token Labeling for Training Better Vision Transformers","created":"2021-04-22","cited_by_count":144},{"id":"2204.12451","title":"Understanding The Robustness in Vision Transformers","created":"2022-04-26","cited_by_count":144},{"id":"2108.00154","title":"CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention","created":"2021-07-31","cited_by_count":139},{"id":"2112.11010","title":"MPViT: Multi-Path Vision Transformer for Dense Prediction","created":"2021-12-21","cited_by_count":122},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117},{"id":"2202.10108","title":"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond","created":"2022-02-21","cited_by_count":117},{"id":"2106.03650","title":"Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer","created":"2021-06-07","cited_by_count":115},{"id":"2105.12723","title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding","created":"2021-05-26","cited_by_count":97},{"id":"2106.05786","title":"CAT: Cross Attention in Vision Transformer","created":"2021-06-10","cited_by_count":92},{"id":"2111.15193","title":"Shunted Self-Attention via Multi-Scale Token Aggregation","created":"2021-11-30","cited_by_count":90},{"id":"2111.13579","title":"VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition","created":"2021-11-26","cited_by_count":65},{"id":"2207.05501","title":"Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios","created":"2022-07-12","cited_by_count":65},{"id":"2106.04263","title":"On the Connection between Local Attention and Dynamic Depth-wise Convolution","created":"2021-06-08","cited_by_count":62},{"id":"2105.15168","title":"MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens","created":"2021-05-31","cited_by_count":46},{"id":"2204.08446","title":"VSA: Learning Varied-Size Window Attention in Vision Transformers","created":"2022-04-18","cited_by_count":43},{"id":"2106.02277","title":"Glance-and-Gaze Vision Transformer","created":"2021-06-04","cited_by_count":42},{"id":"2302.01791","title":"DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition","created":"2023-02-03","cited_by_count":34},{"id":"2109.03810","title":"Scaled ReLU Matters for Training Vision Transformers","created":"2021-09-08","cited_by_count":29},{"id":"2203.12856","title":"Beyond Fixation: Dynamic Window Visual Transformer","created":"2022-03-24","cited_by_count":28},{"id":"2201.12903","title":"Aggregating Global Features into Local Vision Transformer","created":"2022-01-30","cited_by_count":10},{"id":"2112.13085","title":"SimViT: Exploring a Simple Vision Transformer with sliding windows","created":"2021-12-24","cited_by_count":8}],"next_cursor":null}