{"list":"other","total":61,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341},{"id":"2304.08466","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","created":"2023-04-17","cited_by_count":327},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"id":"2302.07944","title":"Effective Data Augmentation With Diffusion Models","created":"2023-02-07","cited_by_count":283},{"id":"2307.06948","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","created":"2023-07-13","cited_by_count":272},{"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":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"2303.11681","title":"DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models","created":"2023-03-21","cited_by_count":162},{"id":"2210.07225","title":"Unified Vision and Language Prompt Learning","created":"2022-10-13","cited_by_count":148},{"id":"2308.06160","title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","created":"2023-08-11","cited_by_count":123},{"id":"1708.01566","title":"Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes","created":"2017-08-04","cited_by_count":122},{"id":"1812.05040","title":"Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach","created":"2018-12-12","cited_by_count":119},{"id":"2110.06558","title":"LENS: Localization enhanced by NeRF synthesis","created":"2021-10-13","cited_by_count":117},{"id":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108},{"id":"2206.09541","title":"DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations","created":"2022-06-20","cited_by_count":102},{"id":"2305.16289","title":"Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation","created":"2023-05-25","cited_by_count":100},{"id":"2304.05390","title":"HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models","created":"2023-04-11","cited_by_count":95},{"id":"2203.05175","title":"MVP: Multimodality-guided Visual Pre-training","created":"2022-03-10","cited_by_count":92},{"id":"2203.01913","title":"NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fields","created":"2022-03-03","cited_by_count":86},{"id":"2311.18231","title":"TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model","created":"2023-11-30","cited_by_count":76},{"id":"2208.02515","title":"Fine-Grained Semantically Aligned Vision-Language Pre-Training","created":"2022-08-04","cited_by_count":68},{"id":"2310.15160","title":"FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models","created":"2023-10-23","cited_by_count":61},{"id":"2309.07439","title":"DePT: Decoupled Prompt Tuning","created":"2023-09-14","cited_by_count":58},{"id":"2306.04607","title":"GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation","created":"2023-06-07","cited_by_count":56},{"id":"2310.00031","title":"Text-image Alignment for Diffusion-based Perception","created":"2023-09-29","cited_by_count":42},{"id":"2405.00740","title":"Modeling Caption Diversity in Contrastive Vision-Language Pretraining","created":"2024-04-30","cited_by_count":42},{"id":"2304.04704","title":"Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition","created":"2023-04-10","cited_by_count":35},{"id":"2307.02138","title":"Prompting Diffusion Representations for Cross-Domain Semantic Segmentation","created":"2023-07-05","cited_by_count":30},{"id":"2407.01400","title":"GalLoP: Learning Global and Local Prompts for Vision-Language Models","created":"2024-07-01","cited_by_count":29},{"id":"2308.12350","title":"Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation","created":"2023-08-23","cited_by_count":27},{"id":"2404.00851","title":"Prompt Learning via Meta-Regularization","created":"2024-04-01","cited_by_count":26},{"id":"2402.10099","title":"Any-Shift Prompting for Generalization over Distributions","created":"2024-02-15","cited_by_count":24},{"id":"2309.03893","title":"DiffusionEngine: Diffusion Model is Scalable Data Engine for Object Detection","created":"2023-09-07","cited_by_count":23},{"id":"2303.06571","title":"Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models","created":"2023-03-12","cited_by_count":21},{"id":"2305.12954","title":"Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?","created":"2023-05-22","cited_by_count":21},{"id":"1411.7911","title":"On Rendering Synthetic Images for Training an Object Detector","created":"2014-11-28","cited_by_count":18},{"id":"2210.13835","title":"Synthetic Data Supervised Salient Object Detection","created":"2022-10-25","cited_by_count":15},{"id":"2409.08518","title":"Anytime Continual Learning for Open Vocabulary Classification","created":"2024-09-13","cited_by_count":8},{"id":"2503.19897","title":"Scaling Down Text Encoders of Text-to-Image Diffusion Models","created":"2025-03-25","cited_by_count":8}],"next_cursor":null}