{"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"2006.06676","title":"Training Generative Adversarial Networks with Limited Data","created":"2020-06-11","cited_by_count":1186},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"1701.07875","title":"Wasserstein GAN","created":"2017-01-26","cited_by_count":639},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"2006.10738","title":"Differentiable Augmentation for Data-Efficient GAN Training","created":"2020-06-18","cited_by_count":363},{"id":"1610.07629","title":"A Learned Representation For Artistic Style","created":"2016-10-24","cited_by_count":341},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"1802.05637","title":"cGANs with Projection Discriminator","created":"2018-02-15","cited_by_count":254},{"id":"2001.00179","title":"DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection","created":"2020-01-01","cited_by_count":233},{"id":"2104.05707","title":"LocalViT: Analyzing Locality in Vision Transformers","created":"2021-04-12","cited_by_count":228},{"id":"2007.08457","title":"Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data","created":"2020-07-16","cited_by_count":201},{"id":"2011.12026","title":"Adversarial Generation of Continuous Images","created":"2020-11-24","cited_by_count":135},{"id":"2002.12655","title":"A U-Net Based Discriminator for Generative Adversarial Networks","created":"2020-02-28","cited_by_count":128},{"id":"2107.04589","title":"ViTGAN: Training GANs with Vision Transformers","created":"2021-07-09","cited_by_count":110},{"id":"1803.01719","title":"How to Start Training: The Effect of Initialization and Architecture","created":"2018-03-05","cited_by_count":109},{"id":"2011.13775","title":"Image Generators with Conditionally-Independent Pixel Synthesis","created":"2020-11-27","cited_by_count":106},{"id":"2002.04724","title":"Improved Consistency Regularization for GANs","created":"2020-02-11","cited_by_count":69},{"id":"2012.05217","title":"Positional Encoding as Spatial Inductive Bias in GANs","created":"2020-12-09","cited_by_count":69},{"id":"1904.00284","title":"COCO-GAN: Generation by Parts via Conditional Coordinating","created":"2019-03-30","cited_by_count":67},{"id":"2010.02917","title":"A Contrastive Learning Approach for Training Variational Autoencoder Priors","created":"2020-10-06","cited_by_count":66},{"id":"2106.07631","title":"Improved Transformer for High-Resolution GANs","created":"2021-06-14","cited_by_count":59},{"id":"2109.02563","title":"3D Human Texture Estimation from a Single Image with Transformers","created":"2021-09-06","cited_by_count":35},{"id":"2106.07023","title":"Styleformer: Transformer based Generative Adversarial Networks with Style Vector","created":"2021-06-13","cited_by_count":27},{"id":"2004.02088","title":"Feature Quantization Improves GAN Training","created":"2020-04-05","cited_by_count":23},{"id":"1911.12287","title":"Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models","created":"2019-11-27","cited_by_count":21},{"id":"1912.04216","title":"cGANs with Multi-Hinge Loss","created":"2019-12-09","cited_by_count":8},{"id":"1711.06491","title":"High-resolution Deep Convolutional Generative Adversarial Networks","created":"2017-11-17","cited_by_count":7},{"id":"2007.06418","title":"Lessons Learned from the Training of GANs on Artificial Datasets","created":"2020-07-13","cited_by_count":5}],"next_cursor":null}