{"list":"other","total":59,"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":"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"1912.12180","title":"Axial Attention in Multidimensional Transformers","created":"2019-12-20","cited_by_count":358},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"id":"2103.11816","title":"Incorporating Convolution Designs into Visual Transformers","created":"2021-03-22","cited_by_count":248},{"id":"2104.05707","title":"LocalViT: Analyzing Locality in Vision Transformers","created":"2021-04-12","cited_by_count":228},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220},{"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":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"2305.10924","title":"Structural Pruning for Diffusion Models","created":"2023-05-18","cited_by_count":195},{"id":"2011.10881","title":"Rethinking Transformer-based Set Prediction for Object Detection","created":"2020-11-21","cited_by_count":156},{"id":"1901.06656","title":"Training Neural Networks with Local Error Signals","created":"2019-01-20","cited_by_count":136},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132},{"id":"2211.10277","title":"Task Residual for Tuning Vision-Language Models","created":"2022-11-18","cited_by_count":123},{"id":"2210.16774","title":"Dataset Distillation via Factorization","created":"2022-10-30","cited_by_count":115},{"id":"2102.05644","title":"Training Vision Transformers for Image Retrieval","created":"2021-02-10","cited_by_count":90},{"id":"2111.15193","title":"Shunted Self-Attention via Multi-Scale Token Aggregation","created":"2021-11-30","cited_by_count":90},{"id":"2205.13213","title":"Fast Vision Transformers with HiLo Attention","created":"2022-05-26","cited_by_count":78},{"id":"2210.17409","title":"Deep Model Reassembly","created":"2022-10-24","cited_by_count":78},{"id":"2207.03337","title":"Factorizing Knowledge in Neural Networks","created":"2022-07-04","cited_by_count":59},{"id":"2303.01610","title":"Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers","created":"2023-03-02","cited_by_count":59},{"id":"2106.12378","title":"Co-advise: Cross Inductive Bias Distillation","created":"2021-06-23","cited_by_count":40},{"id":"2206.06801","title":"Peripheral Vision Transformer","created":"2022-06-14","cited_by_count":27},{"id":"2206.07692","title":"A Simple Data Mixing Prior for Improving Self-Supervised Learning","created":"2022-06-15","cited_by_count":27},{"id":"2301.01296","title":"TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models","created":"2023-01-03","cited_by_count":24},{"id":"2305.12972","title":"VanillaNet: the Power of Minimalism in Deep Learning","created":"2023-05-22","cited_by_count":23},{"id":"2207.13317","title":"Convolutional Embedding Makes Hierarchical Vision Transformer Stronger","created":"2022-07-27","cited_by_count":10},{"id":"2204.07366","title":"ResT V2: Simpler, Faster and Stronger","created":"2022-04-15","cited_by_count":9}],"next_cursor":null}