{"list":"other","total":68,"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"2012.09688","title":"PCT: Point cloud transformer","created":"2020-12-17","cited_by_count":732},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"1604.03539","title":"Cross-stitch Networks for Multi-task Learning","created":"2016-04-12","cited_by_count":467},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"1905.07553","title":"Which Tasks Should Be Learned Together in Multi-task Learning?","created":"2019-05-18","cited_by_count":375},{"id":"1901.11504","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","created":"2019-01-31","cited_by_count":350},{"id":"2006.04139","title":"Learning Texture Transformer Network for Image Super-Resolution","created":"2020-06-07","cited_by_count":347},{"id":"2103.16716","title":"BASE Layers: Simplifying Training of Large, Sparse Models","created":"2021-03-30","cited_by_count":320},{"id":"1312.4314","title":"Learning Factored Representations in a Deep Mixture of Experts","created":"2013-12-16","cited_by_count":278},{"id":"1904.04971","title":"CondConv: Conditionally Parameterized Convolutions for Efficient Inference","created":"2019-04-10","cited_by_count":273},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237},{"id":"1805.04409","title":"PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing","created":"2018-05-11","cited_by_count":224},{"id":"1606.01933","title":"A Decomposable Attention Model for Natural Language Inference","created":"2016-06-06","cited_by_count":215},{"id":"2010.06808","title":"Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout","created":"2020-10-14","cited_by_count":201},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183},{"id":"1511.06342","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","created":"2015-11-19","cited_by_count":178},{"id":"2010.05874","title":"Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models","created":"2020-10-12","cited_by_count":169},{"id":"2102.07074","title":"TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up","created":"2021-02-14","cited_by_count":162},{"id":"2001.06902","title":"MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning","created":"2020-01-19","cited_by_count":157},{"id":"1906.03525","title":"Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation","created":"2019-06-08","cited_by_count":142},{"id":"2203.05962","title":"Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice","created":"2022-03-09","cited_by_count":136},{"id":"1801.08297","title":"NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction","created":"2018-01-25","cited_by_count":127},{"id":"2106.03760","title":"DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning","created":"2021-06-07","cited_by_count":115},{"id":"2207.13298","title":"Is Attention All That NeRF Needs?","created":"2022-07-27","cited_by_count":113},{"id":"2107.04589","title":"ViTGAN: Training GANs with Vision Transformers","created":"2021-07-09","cited_by_count":110},{"id":"2207.05736","title":"Vision Transformer for NeRF-Based View Synthesis from a Single Input Image","created":"2022-07-12","cited_by_count":104},{"id":"1706.05137","title":"One Model To Learn Them All","created":"2017-06-16","cited_by_count":87},{"id":"2111.12763","title":"Sparse is Enough in Scaling Transformers","created":"2021-11-24","cited_by_count":86},{"id":"1305.0445","title":"Deep Learning of Representations: Looking Forward","created":"2013-05-02","cited_by_count":84},{"id":"2012.09958","title":"Toward Transformer-Based Object Detection","created":"2020-12-17","cited_by_count":84},{"id":"1611.01587","title":"A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks","created":"2016-11-05","cited_by_count":62},{"id":"1604.06119","title":"Network of Experts for Large-Scale Image Categorization","created":"2016-04-20","cited_by_count":54},{"id":"2007.08563","title":"FTRANS: Energy-Efficient Acceleration of Transformers using FPGA","created":"2020-07-16","cited_by_count":54},{"id":"2009.09139","title":"Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data","created":"2020-09-19","cited_by_count":50},{"id":"2203.16708","title":"Task Adaptive Parameter Sharing for Multi-Task Learning","created":"2022-03-30","cited_by_count":42},{"id":"2201.06618","title":"VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer","created":"2022-01-17","cited_by_count":27},{"id":"1805.02165","title":"Joint CS-MRI Reconstruction and Segmentation with a Unified Deep Network","created":"2018-05-06","cited_by_count":21},{"id":"2106.10595","title":"Heterogeneous Multi-task Learning with Expert Diversity","created":"2021-06-20","cited_by_count":18},{"id":"2110.08246","title":"Tricks for Training Sparse Translation Models","created":"2021-10-15","cited_by_count":17},{"id":"2110.15926","title":"Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems","created":"2021-10-29","cited_by_count":3}],"next_cursor":null}