{"list":"other","total":60,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"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":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"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":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1604.03539","title":"Cross-stitch Networks for Multi-task Learning","created":"2016-04-12","cited_by_count":467},{"id":"1905.07553","title":"Which Tasks Should Be Learned Together in Multi-task Learning?","created":"2019-05-18","cited_by_count":375},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"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":"2104.06399","title":"Co-Scale Conv-Attentional Image Transformers","created":"2021-04-13","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":"1902.03545","title":"Task2Vec: Task Embedding for Meta-Learning","created":"2019-02-10","cited_by_count":205},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195},{"id":"2001.06902","title":"MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning","created":"2020-01-19","cited_by_count":157},{"id":"2203.02891","title":"Multi-class Token Transformer for Weakly Supervised Semantic Segmentation","created":"2022-03-06","cited_by_count":138},{"id":"2111.11429","title":"Benchmarking Detection Transfer Learning with Vision Transformers","created":"2021-11-22","cited_by_count":131},{"id":"2011.14027","title":"General Multi-label Image Classification with Transformers","created":"2020-11-27","cited_by_count":127},{"id":"2106.02689","title":"RegionViT: Regional-to-Local Attention for Vision Transformers","created":"2021-06-04","cited_by_count":127},{"id":"2103.12091","title":"Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction","created":"2021-03-22","cited_by_count":125},{"id":"2005.09814","title":"Mirror Descent Policy Optimization","created":"2020-05-20","cited_by_count":106},{"id":"2006.04096","title":"Robust Learning Through Cross-Task Consistency","created":"2020-06-07","cited_by_count":105},{"id":"2203.07997","title":"InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding","created":"2022-03-15","cited_by_count":89},{"id":"1904.11740","title":"Representation Similarity Analysis for Efficient Task taxonomy & Transfer Learning","created":"2019-04-26","cited_by_count":86},{"id":"2204.05525","title":"TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation","created":"2022-04-12","cited_by_count":82},{"id":"2104.13874","title":"Exploring Relational Context for Multi-Task Dense Prediction","created":"2021-04-28","cited_by_count":71},{"id":"2205.08303","title":"MulT: An End-to-End Multitask Learning Transformer","created":"2022-05-17","cited_by_count":48},{"id":"1711.03665","title":"Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency","created":"2017-11-10","cited_by_count":40},{"id":"2108.00616","title":"RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth","created":"2021-08-02","cited_by_count":33},{"id":"2105.07830","title":"Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation","created":"2021-05-17","cited_by_count":32},{"id":"2105.14173","title":"FoveaTer: Foveated Transformer for Image Classification","created":"2021-05-29","cited_by_count":28},{"id":"1903.01092","title":"Zero-Shot Task Transfer","created":"2019-03-04","cited_by_count":26},{"id":"2206.08927","title":"DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning","created":"2022-06-17","cited_by_count":25},{"id":"2105.14095","title":"Weighted Training for Cross-Task Learning","created":"2021-05-28","cited_by_count":22},{"id":"2106.11401","title":"Spatio-Temporal Multi-Task Learning Transformer for Joint Moving Object Detection and Segmentation","created":"2021-06-21","cited_by_count":9},{"id":"1908.00061","title":"An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation","created":"2019-07-31","cited_by_count":4}],"next_cursor":null}