{"list":"other","total":78,"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":"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"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":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"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":"1904.01169","title":"Res2Net: A New Multi-scale Backbone Architecture","created":"2019-04-02","cited_by_count":470},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"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":"2201.00520","title":"Vision Transformer with Deformable Attention","created":"2022-01-03","cited_by_count":295},{"id":"2201.09450","title":"UniFormer: Unifying Convolution and Self-attention for Visual Recognition","created":"2022-01-24","cited_by_count":206},{"id":"2305.07027","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention","created":"2023-05-11","cited_by_count":172},{"id":"2303.08810","title":"BiFormer: Vision Transformer with Bi-Level Routing Attention","created":"2023-03-15","cited_by_count":151},{"id":"2105.07926","title":"Towards Robust Vision Transformer","created":"2021-05-17","cited_by_count":137},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117},{"id":"2106.12368","title":"Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition","created":"2021-06-23","cited_by_count":103},{"id":"2111.15193","title":"Shunted Self-Attention via Multi-Scale Token Aggregation","created":"2021-11-30","cited_by_count":90},{"id":"2105.13677","title":"ResT: An Efficient Transformer for Visual Recognition","created":"2021-05-28","cited_by_count":79},{"id":"2205.13213","title":"Fast Vision Transformers with HiLo Attention","created":"2022-05-26","cited_by_count":78},{"id":"2207.04978","title":"Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning","created":"2022-07-11","cited_by_count":78},{"id":"2311.18257","title":"Diffusion Models Without Attention","created":"2023-11-30","cited_by_count":75},{"id":"2306.07303","title":"A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks","created":"2023-06-11","cited_by_count":71},{"id":"2308.06873","title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer","created":"2023-08-14","cited_by_count":64},{"id":"2203.03821","title":"CF-ViT: A General Coarse-to-Fine Method for Vision Transformer","created":"2022-03-08","cited_by_count":63},{"id":"2111.12294","title":"An Image Patch is a Wave: Phase-Aware Vision MLP","created":"2021-11-24","cited_by_count":61},{"id":"1705.01450","title":"Gabor Convolutional Networks","created":"2017-05-03","cited_by_count":55},{"id":"2105.14217","title":"Less is More: Pay Less Attention in Vision Transformers","created":"2021-05-29","cited_by_count":53},{"id":"2303.15105","title":"Vision Transformer with Quadrangle Attention","created":"2023-03-27","cited_by_count":46},{"id":"2211.11167","title":"Vision Transformer with Super Token Sampling","created":"2022-11-21","cited_by_count":44},{"id":"2204.02557","title":"MixFormer: Mixing Features across Windows and Dimensions","created":"2022-04-06","cited_by_count":43},{"id":"2309.02031","title":"A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking","created":"2023-09-05","cited_by_count":41},{"id":"2304.04237","title":"Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention","created":"2023-04-09","cited_by_count":38},{"id":"2203.10790","title":"ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer","created":"2022-03-21","cited_by_count":36},{"id":"2308.12216","title":"SG-Former: Self-guided Transformer with Evolving Token Reallocation","created":"2023-08-23","cited_by_count":32},{"id":"2203.05922","title":"Visualizing and Understanding Patch Interactions in Vision Transformer","created":"2022-03-11","cited_by_count":26},{"id":"2209.01634","title":"Single-source Domain Expansion Network for Cross-Scene Hyperspectral Image Classification","created":"2022-09-04","cited_by_count":25},{"id":"2306.00396","title":"Lightweight Vision Transformer with Bidirectional Interaction","created":"2023-06-01","cited_by_count":25},{"id":"2308.03005","title":"MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation","created":"2023-08-06","cited_by_count":22},{"id":"2303.06908","title":"CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention","created":"2023-03-13","cited_by_count":18},{"id":"2308.05396","title":"Learning Gabor Texture Features for Fine-Grained Recognition","created":"2023-08-10","cited_by_count":16},{"id":"2310.04180","title":"Degradation-Aware Self-Attention Based Transformer for Blind Image Super-Resolution","created":"2023-10-06","cited_by_count":14},{"id":"2306.14287","title":"Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image Compression","created":"2023-06-25","cited_by_count":13},{"id":"2307.11458","title":"Strip-MLP: Efficient Token Interaction for Vision MLP","created":"2023-07-21","cited_by_count":12},{"id":"2202.06268","title":"BViT: Broad Attention based Vision Transformer","created":"2022-02-13","cited_by_count":10},{"id":"1912.05661","title":"Gabor Layers Enhance Network Robustness","created":"2019-12-11","cited_by_count":9},{"id":"1912.03991","title":"Naive Gabor Networks for Hyperspectral Image Classification","created":"2019-12-09","cited_by_count":5},{"id":"2310.10602","title":"Physics-informed neural wavefields with Gabor basis functions","created":"2023-10-16","cited_by_count":5},{"id":"2312.08614","title":"Factorization Vision Transformer: Modeling Long Range Dependency with Local Window Cost","created":"2023-12-14","cited_by_count":5},{"id":"2308.07661","title":"Attention Is Not All You Need Anymore","created":"2023-08-15","cited_by_count":1},{"id":"2310.06629","title":"EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention","created":"2023-10-10","cited_by_count":1}],"next_cursor":null}