{"list":"other","total":54,"rows":[{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"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":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"1905.07553","title":"Which Tasks Should Be Learned Together in Multi-task Learning?","created":"2019-05-18","cited_by_count":375},{"id":"2009.09796","title":"Multi-Task Learning with Deep Neural Networks: A Survey","created":"2020-09-10","cited_by_count":375},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"id":"2104.09937","title":"Gradient Matching for Domain Generalization","created":"2021-04-20","cited_by_count":258},{"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":"2109.04617","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","created":"2021-09-10","cited_by_count":222},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215},{"id":"1902.03545","title":"Task2Vec: Task Embedding for Meta-Learning","created":"2019-02-10","cited_by_count":205},{"id":"2206.02770","title":"Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts","created":"2022-06-06","cited_by_count":203},{"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":"2101.12176","title":"On the Origin of Implicit Regularization in Stochastic Gradient Descent","created":"2021-01-28","cited_by_count":184},{"id":"2001.06902","title":"MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning","created":"2020-01-19","cited_by_count":157},{"id":"1904.08918","title":"Attentive Single-Tasking of Multiple Tasks","created":"2019-04-18","cited_by_count":148},{"id":"1906.03525","title":"Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation","created":"2019-06-08","cited_by_count":142},{"id":"2108.00154","title":"CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention","created":"2021-07-31","cited_by_count":139},{"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":"1512.04412","title":"Instance-aware Semantic Segmentation via Multi-task Network Cascades","created":"2015-12-14","cited_by_count":121},{"id":"2006.01895","title":"Learning to Branch for Multi-Task Learning","created":"2020-06-02","cited_by_count":115},{"id":"2210.14793","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design","created":"2022-10-26","cited_by_count":98},{"id":"1611.05377","title":"Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification","created":"2016-11-16","cited_by_count":93},{"id":"2203.07997","title":"InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding","created":"2022-03-15","cited_by_count":89},{"id":"2103.02631","title":"RotoGrad: Gradient Homogenization in Multitask Learning","created":"2021-03-03","cited_by_count":83},{"id":"2306.03792","title":"FAMO: Fast Adaptive Multitask Optimization","created":"2023-06-06","cited_by_count":78},{"id":"1904.02920","title":"Branched Multi-Task Networks: Deciding What Layers To Share","created":"2019-04-05","cited_by_count":76},{"id":"2305.19000","title":"Independent Component Alignment for Multi-Task Learning","created":"2023-05-30","cited_by_count":70},{"id":"2210.05144","title":"Mixture of Attention Heads: Selecting Attention Heads Per Token","created":"2022-10-11","cited_by_count":60},{"id":"2008.10292","title":"Automated Search for Resource-Efficient Branched Multi-Task Networks","created":"2020-08-24","cited_by_count":51},{"id":"2205.08303","title":"MulT: An End-to-End Multitask Learning Transformer","created":"2022-05-17","cited_by_count":48},{"id":"2307.15324","title":"TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts","created":"2023-07-28","cited_by_count":45},{"id":"1904.03292","title":"The Information Complexity of Learning Tasks, their Structure and their Distance","created":"2019-04-05","cited_by_count":36},{"id":"2205.14354","title":"Multi-Task Learning with Multi-Query Transformer for Dense Prediction","created":"2022-05-28","cited_by_count":34},{"id":"2205.09797","title":"Improving Multi-Task Generalization via Regularizing Spurious Correlation","created":"2022-05-19","cited_by_count":28},{"id":"2301.12618","title":"ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning","created":"2023-01-30","cited_by_count":28},{"id":"2301.03461","title":"DeMT: Deformable Mixer Transformer for Multi-Task Learning of Dense Prediction","created":"2023-01-09","cited_by_count":27},{"id":"2004.01377","title":"Sequential Learning for Domain Generalization","created":"2020-04-03","cited_by_count":26},{"id":"1806.08028","title":"Gradient Adversarial Training of Neural Networks","created":"2018-06-21","cited_by_count":17},{"id":"2211.13723","title":"Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective","created":"2022-11-24","cited_by_count":15},{"id":"2405.16560","title":"Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models","created":"2024-05-26","cited_by_count":12},{"id":"2406.02996","title":"Quantifying Task Priority for Multi-Task Optimization","created":"2024-06-05","cited_by_count":11}],"next_cursor":null}