{"list":"other","total":51,"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"1712.02560","title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","created":"2017-12-07","cited_by_count":683},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"id":"1802.10349","title":"Learning to Adapt Structured Output Space for Semantic Segmentation","created":"2018-02-28","cited_by_count":584},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"2304.08466","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","created":"2023-04-17","cited_by_count":327},{"id":"2307.10816","title":"BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion","created":"2023-07-20","cited_by_count":282},{"id":"2303.17189","title":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation","created":"2023-03-30","cited_by_count":259},{"id":"2201.01293","title":"A Transformer-Based Siamese Network for Change Detection","created":"2022-01-04","cited_by_count":244},{"id":"2012.02951","title":"FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding","created":"2020-12-05","cited_by_count":181},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177},{"id":"2212.08420","title":"Fake it till you make it: Learning transferable representations from synthetic ImageNet clones","created":"2022-12-16","cited_by_count":172},{"id":"1911.09296","title":"xBD: A Dataset for Assessing Building Damage from Satellite Imagery","created":"2019-11-21","cited_by_count":139},{"id":"2207.00050","title":"Semantic Image Synthesis via Diffusion Models","created":"2022-06-30","cited_by_count":132},{"id":"2109.06165","title":"CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation","created":"2021-09-13","cited_by_count":129},{"id":"2309.14303","title":"Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation","created":"2023-09-25","cited_by_count":112},{"id":"2210.10732","title":"OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping","created":"2022-10-19","cited_by_count":82},{"id":"2309.13415","title":"Dream the Impossible: Outlier Imagination with Diffusion Models","created":"2023-09-23","cited_by_count":77},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71},{"id":"2310.15160","title":"FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models","created":"2023-10-23","cited_by_count":61},{"id":"2305.18583","title":"Controllable Text-to-Image Generation with GPT-4","created":"2023-05-29","cited_by_count":59},{"id":"2303.13434","title":"Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective","created":"2023-03-23","cited_by_count":54},{"id":"2107.12283","title":"Continental-Scale Building Detection from High Resolution Satellite Imagery","created":"2021-07-26","cited_by_count":50},{"id":"2305.15316","title":"Training on Thin Air: Improve Image Classification with Generated Data","created":"2023-05-24","cited_by_count":50},{"id":"1910.06444","title":"Building Damage Detection in Satellite Imagery Using Convolutional Neural Networks","created":"2019-10-14","cited_by_count":34},{"id":"2306.07200","title":"Fill-Up: Balancing Long-Tailed Data with Generative Models","created":"2023-06-12","cited_by_count":34},{"id":"2004.05525","title":"Building Disaster Damage Assessment in Satellite Imagery with Multi-Temporal Fusion","created":"2020-04-12","cited_by_count":27},{"id":"2201.04236","title":"Incidents1M: a large-scale dataset of images with natural disasters, damage, and incidents","created":"2022-01-11","cited_by_count":26},{"id":"2004.07312","title":"RescueNet: Joint Building Segmentation and Damage Assessment from Satellite Imagery","created":"2020-04-15","cited_by_count":24},{"id":"2207.09988","title":"DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation","created":"2022-07-20","cited_by_count":23},{"id":"2312.02253","title":"Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images","created":"2023-12-04","cited_by_count":20},{"id":"2207.12389","title":"MemSAC: Memory Augmented Sample Consistency for Large Scale Unsupervised Domain Adaptation","created":"2022-07-25","cited_by_count":15},{"id":"2011.10328","title":"Assessing out-of-domain generalization for robust building damage detection","created":"2020-11-20","cited_by_count":13},{"id":"2011.14004","title":"Assessing Post-Disaster Damage from Satellite Imagery using Semi-Supervised Learning Techniques","created":"2020-11-24","cited_by_count":10},{"id":"2309.05956","title":"Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentation","created":"2023-09-12","cited_by_count":10},{"id":"2108.08955","title":"CIGLI: Conditional Image Generation from Language & Image","created":"2021-08-20","cited_by_count":3},{"id":"2403.05170","title":"DiffuLT: How to Make Diffusion Model Useful for Long-tail Recognition","created":"2024-03-08","cited_by_count":3},{"id":"2111.06812","title":"Sci-Net: Scale Invariant Model for Buildings Segmentation from Aerial Imagery","created":"2021-11-12","cited_by_count":2}],"next_cursor":null}