{"list":"other","total":52,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"2112.03126","title":"Label-Efficient Semantic Segmentation with Diffusion Models","created":"2021-12-06","cited_by_count":499},{"id":"2006.06882","title":"Rethinking Pre-training and Self-training","created":"2020-06-11","cited_by_count":352},{"id":"2306.09683","title":"Scaling Open-Vocabulary Object Detection","created":"2023-06-16","cited_by_count":343},{"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":"2302.07944","title":"Effective Data Augmentation With Diffusion Models","created":"2023-02-07","cited_by_count":283},{"id":"2309.15807","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","created":"2023-09-27","cited_by_count":279},{"id":"2302.11550","title":"Scaling Robot Learning with Semantically Imagined Experience","created":"2023-02-22","cited_by_count":177},{"id":"2103.05950","title":"FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding","created":"2021-03-10","cited_by_count":168},{"id":"2309.03895","title":"InstructDiffusion: A Generalist Modeling Interface for Vision Tasks","created":"2023-09-07","cited_by_count":164},{"id":"2404.07987","title":"ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback","created":"2024-04-11","cited_by_count":154},{"id":"1805.07722","title":"Task-Agnostic Meta-Learning for Few-shot Learning","created":"2018-05-20","cited_by_count":151},{"id":"2303.11306","title":"Localizing Object-level Shape Variations with Text-to-Image Diffusion Models","created":"2023-03-20","cited_by_count":142},{"id":"2308.06160","title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","created":"2023-08-11","cited_by_count":123},{"id":"2305.09972","title":"Real-Time Flying Object Detection with YOLOv8","created":"2023-05-17","cited_by_count":94},{"id":"2211.15462","title":"Investigating Prompt Engineering in Diffusion Models","created":"2022-11-21","cited_by_count":58},{"id":"2104.07719","title":"Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment","created":"2021-04-15","cited_by_count":57},{"id":"2402.05937","title":"InstaGen: Enhancing Object Detection by Training on Synthetic Dataset","created":"2024-02-08","cited_by_count":26},{"id":"2406.08249","title":"Dataset Enhancement with Instance-Level Augmentations","created":"2024-06-12","cited_by_count":23},{"id":"2305.11818","title":"MaGIC: Multi-modality Guided Image Completion","created":"2023-05-19","cited_by_count":14},{"id":"2312.04566","title":"Gen2Det: Generate to Detect","created":"2023-12-07","cited_by_count":12},{"id":"2403.09468","title":"Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editing","created":"2024-03-14","cited_by_count":12},{"id":"2204.07841","title":"Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting","created":"2022-04-16","cited_by_count":11},{"id":"2310.16794","title":"Using Diffusion Models to Generate Synthetic Labelled Data for Medical Image Segmentation","created":"2023-10-25","cited_by_count":10},{"id":"2211.13993","title":"Combating noisy labels in object detection datasets","created":"2022-11-25","cited_by_count":8},{"id":"2208.07039","title":"Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning","created":"2022-08-15","cited_by_count":6},{"id":"2404.17033","title":"Auto-Generating Weak Labels for Real & Synthetic Data to Improve Label-Scarce Medical Image Segmentation","created":"2024-04-25","cited_by_count":3}],"next_cursor":null}