{"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"id":"1612.00603","title":"A Point Set Generation Network for 3D Object Reconstruction from a Single Image","created":"2016-12-02","cited_by_count":979},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"1804.04732","title":"Multimodal Unsupervised Image-to-Image Translation","created":"2018-04-12","cited_by_count":795},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"2011.09157","title":"Dense Contrastive Learning for Self-Supervised Visual Pre-Training","created":"2020-11-18","cited_by_count":512},{"id":"1710.06924","title":"VisDA: The Visual Domain Adaptation Challenge","created":"2017-10-18","cited_by_count":435},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"1604.05144","title":"ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation","created":"2016-04-18","cited_by_count":331},{"id":"2104.06490","title":"DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort","created":"2021-04-13","cited_by_count":264},{"id":"1608.08614","title":"What makes ImageNet good for transfer learning?","created":"2016-08-30","cited_by_count":192},{"id":"2011.05499","title":"Unsupervised Learning of Dense Visual Representations","created":"2020-11-11","cited_by_count":147},{"id":"2104.05833","title":"Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization","created":"2021-04-12","cited_by_count":141},{"id":"1904.11621","title":"Meta-Sim: Learning to Generate Synthetic Datasets","created":"2019-04-25","cited_by_count":128},{"id":"1711.09081","title":"Deep Extreme Cut: From Extreme Points to Object Segmentation","created":"2017-11-24","cited_by_count":127},{"id":"1804.01346","title":"Normalized Cut Loss for Weakly-supervised CNN Segmentation","created":"2018-04-04","cited_by_count":112},{"id":"2103.12902","title":"Region Similarity Representation Learning","created":"2021-03-24","cited_by_count":96},{"id":"1903.06874","title":"Fast Interactive Object Annotation with Curve-GCN","created":"2019-03-16","cited_by_count":95},{"id":"2103.04379","title":"Repurposing GANs for One-shot Semantic Part Segmentation","created":"2021-03-07","cited_by_count":88},{"id":"2103.13517","title":"A Broad Study on the Transferability of Visual Representations with Contrastive Learning","created":"2021-03-24","cited_by_count":78},{"id":"2105.06464","title":"DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision","created":"2021-05-13","cited_by_count":59},{"id":"2008.09092","title":"Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation","created":"2020-08-20","cited_by_count":58},{"id":"1904.07934","title":"Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations","created":"2019-04-16","cited_by_count":32},{"id":"1809.02882","title":"Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection","created":"2018-09-08","cited_by_count":28},{"id":"2104.00487","title":"Linear Semantics in Generative Adversarial Networks","created":"2021-04-01","cited_by_count":25},{"id":"1803.01199","title":"Chest X-Ray Analysis of Tuberculosis by Deep Learning with Segmentation and Augmentation","created":"2018-03-03","cited_by_count":24},{"id":"2009.00668","title":"Fed-Sim: Federated Simulation for Medical Imaging","created":"2020-09-01","cited_by_count":14},{"id":"2006.10451","title":"Learning High-Resolution Domain-Specific Representations with a GAN Generator","created":"2020-06-18","cited_by_count":9}],"next_cursor":null}