{"total":151,"rows":[{"id":"2401.16380","title":"Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling","created":"2024-01-29","cited_by_count":161,"area":null},{"id":"2405.11656","title":"URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Images","created":"2024-05-19","cited_by_count":111,"area":null},{"id":"2305.16289","title":"Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation","created":"2023-05-25","cited_by_count":100,"area":null},{"id":"2310.15160","title":"FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models","created":"2023-10-23","cited_by_count":61,"area":null},{"id":"2405.09591","title":"A Comprehensive Survey on Data Augmentation","created":"2024-05-15","cited_by_count":40,"area":null},{"id":"2309.14356","title":"COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs","created":"2023-09-23","cited_by_count":39,"area":null},{"id":"2403.05854","title":"LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content","created":"2024-03-09","cited_by_count":33,"area":null},{"id":"2305.17476","title":"Toward Understanding Generative Data Augmentation","created":"2023-05-27","cited_by_count":25,"area":null},{"id":"2403.05016","title":"DiffClass: Diffusion-Based Class Incremental Learning","created":"2024-03-08","cited_by_count":23,"area":null},{"id":"2308.12288","title":"CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images","created":"2023-08-23","cited_by_count":19,"area":null},{"id":"2501.06907","title":"Deep Learning and Foundation Models for Weather Prediction: A Survey","created":"2025-01-12","cited_by_count":16,"area":null},{"id":"2308.00994","title":"SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems","created":"2023-08-02","cited_by_count":13,"area":null},{"id":"2310.01830","title":"AI-Generated Images as Data Source: The Dawn of Synthetic Era","created":"2023-10-03","cited_by_count":13,"area":null},{"id":"2401.04716","title":"Low-Resource Vision Challenges for Foundation Models","created":"2024-01-09","cited_by_count":13,"area":null},{"id":"2403.06168","title":"DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotation","created":"2024-03-10","cited_by_count":13,"area":null},{"id":"2410.17606","title":"Towards Effective Data-Free Knowledge Distillation via Diverse Diffusion Augmentation","created":"2024-10-23","cited_by_count":13,"area":null},{"id":"2308.07151","title":"Diffusion Based Augmentation for Captioning and Retrieval in Cultural Heritage","created":"2023-08-14","cited_by_count":12,"area":null},{"id":"2406.14551","title":"Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation","created":"2024-06-20","cited_by_count":12,"area":null},{"id":"2409.00547","title":"Data Augmentation for Image Classification using Generative AI","created":"2024-08-31","cited_by_count":11,"area":null},{"id":"2503.15485","title":"TULIP: Towards Unified Language-Image Pretraining","created":"2025-03-19","cited_by_count":11,"area":null},{"id":"2506.05127","title":"PixCell: A generative foundation model for digital histopathology images","created":"2025-06-05","cited_by_count":11,"area":null},{"id":"2305.10308","title":"Rethinking Data Augmentation for Tabular Data in Deep Learning","created":"2023-05-17","cited_by_count":10,"area":null},{"id":"2312.03475","title":"Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion","created":"2023-12-06","cited_by_count":10,"area":null},{"id":"2412.16839","title":"Human-Guided Image Generation for Expanding Small-Scale Training Image Datasets","created":"2024-12-22","cited_by_count":10,"area":null},{"id":"2507.04051","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","created":"2025-07-05","cited_by_count":10,"area":null},{"id":"2403.12003","title":"GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised Learning","created":"2024-03-18","cited_by_count":9,"area":null},{"id":"2410.01322","title":"Forte : Finding Outliers with Representation Typicality Estimation","created":"2024-10-02","cited_by_count":9,"area":null},{"id":"2412.16156","title":"Personalized Representation from Personalized Generation","created":"2024-12-20","cited_by_count":9,"area":null},{"id":"2403.06517","title":"Active Generation for Image Classification","created":"2024-03-11","cited_by_count":8,"area":null},{"id":"2308.04288","title":"Cloth2Tex: A Customized Cloth Texture Generation Pipeline for 3D Virtual Try-On","created":"2023-08-08","cited_by_count":7,"area":null},{"id":"2510.08123","title":"High-dimensional Analysis of Synthetic Data Selection","created":"2025-10-09","cited_by_count":7,"area":null},{"id":"2603.18534","title":"Data-efficient pre-training by scaling synthetic megadocs","created":"2026-03-19","cited_by_count":7,"area":null},{"id":"2405.19822","title":"Improving Object Detector Training on Synthetic Data by Starting With a Strong Baseline Methodology","created":"2024-05-30","cited_by_count":6,"area":null},{"id":"2411.02592","title":"Decoupled Data Augmentation for Improving Image Classification","created":"2024-10-29","cited_by_count":6,"area":null},{"id":"2412.14462","title":"Affordance-Aware Object Insertion via Mask-Aware Dual Diffusion","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2509.20745","title":"Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection","created":"2025-09-25","cited_by_count":6,"area":null},{"id":"2306.09192","title":"DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers","created":"2023-06-15","cited_by_count":5,"area":null},{"id":"2308.10103","title":"ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations","created":"2023-08-19","cited_by_count":5,"area":null},{"id":"2403.07356","title":"Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning","created":"2024-03-12","cited_by_count":5,"area":null},{"id":"2409.07003","title":"ODYSSEE: Oyster Detection Yielded by Sensor Systems on Edge Electronics","created":"2024-09-11","cited_by_count":5,"area":null},{"id":"2411.05223","title":"Generalizable Single-Source Cross-modality Medical Image Segmentation via Invariant Causal Mechanisms","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2305.15026","title":"Transferring Visual Attributes from Natural Language to Verified Image Generation","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2308.02606","title":"Improving Human-Object Interaction Detection via Virtual Image Learning","created":"2023-08-04","cited_by_count":4,"area":null},{"id":"2310.00277","title":"A Unified Framework for Generative Data Augmentation: A Comprehensive Survey","created":"2023-09-30","cited_by_count":4,"area":null},{"id":"2310.02520","title":"MedDiffusion: Boosting Health Risk Prediction via Diffusion-based Data Augmentation","created":"2023-10-04","cited_by_count":4,"area":null},{"id":"2312.13440","title":"MGAug: Multimodal Geometric Augmentation in Latent Spaces of Image Deformations","created":"2023-12-20","cited_by_count":4,"area":null},{"id":"2404.16421","title":"SynCellFactory: Generative Data Augmentation for Cell Tracking","created":"2024-04-25","cited_by_count":4,"area":null},{"id":"2404.18933","title":"Learning Low-Rank Feature for Thorax Disease Classification","created":"2024-02-14","cited_by_count":4,"area":null},{"id":"2407.08209","title":"Enriching Information and Preserving Semantic Consistency in Expanding Curvilinear Object Segmentation Datasets","created":"2024-07-11","cited_by_count":4,"area":null},{"id":"2409.17091","title":"Ctrl-GenAug: Controllable Generative Augmentation for Medical Sequence Classification","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2412.07199","title":"A Parametric Approach to Adversarial Augmentation for Cross-Domain Iris Presentation Attack Detection","created":"2024-12-10","cited_by_count":4,"area":null},{"id":"2510.18229","title":"Unbiased Object Detection Beyond Frequency with Visually Prompted Image Synthesis","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2311.09401","title":"MoCo-Transfer: Investigating out-of-distribution contrastive learning for limited-data domains","created":"2023-11-15","cited_by_count":3,"area":null},{"id":"2401.10754","title":"Data Augmentation for Traffic Classification","created":"2024-01-19","cited_by_count":3,"area":null},{"id":"2402.11305","title":"On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models","created":"2024-02-17","cited_by_count":3,"area":null},{"id":"2410.21153","title":"Synthetica: Large Scale Synthetic Data for Robot Perception","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2412.04748","title":"Decomposed Distribution Matching in Dataset Condensation","created":"2024-12-06","cited_by_count":3,"area":null},{"id":"2501.13372","title":"Generative Data Augmentation Challenge: Zero-Shot Speech Synthesis for Personalized Speech Enhancement","created":"2025-01-23","cited_by_count":3,"area":null},{"id":"2504.07560","title":"PhaseGen: A Diffusion-Based Approach for Complex-Valued MRI Data Generation","created":"2025-04-10","cited_by_count":3,"area":null},{"id":"2509.21479","title":"Filtering with Confidence: When Data Augmentation Meets Conformal Prediction","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2311.14764","title":"SafeSea: Synthetic Data Generation for Adverse & Low Probability Maritime Conditions","created":"2023-11-24","cited_by_count":2,"area":null},{"id":"2401.00420","title":"SynCDR : Training Cross Domain Retrieval Models with Synthetic Data","created":"2023-12-31","cited_by_count":2,"area":null},{"id":"2404.03144","title":"Diverse and Tailored Image Generation for Zero-shot Multi-label Classification","created":"2024-04-04","cited_by_count":2,"area":null},{"id":"2405.03702","title":"Leafy Spurge Dataset: Real-world Weed Classification Within Aerial Drone Imagery","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2406.12368","title":"MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2409.01109","title":"SOOD-ImageNet: a Large-Scale Dataset for Semantic Out-Of-Distribution Image Classification and Semantic Segmentation","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2409.06002","title":"Enhanced Generative Data Augmentation for Semantic Segmentation via Stronger Guidance","created":"2024-09-09","cited_by_count":2,"area":null},{"id":"2409.07796","title":"WildFit: Autonomous In-situ Model Adaptation for Resource-Constrained IoT Systems","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2409.09424","title":"NBBOX: Noisy Bounding Box Improves Remote Sensing Object Detection","created":"2024-09-14","cited_by_count":2,"area":null},{"id":"2410.11963","title":"CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2412.04668","title":"Diffusion-Augmented Coreset Expansion for Scalable Dataset Distillation","created":"2024-12-05","cited_by_count":2,"area":null},{"id":"2501.02048","title":"DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data","created":"2025-01-03","cited_by_count":2,"area":null},{"id":"2503.09399","title":"ForAug: Mitigating Biases in Image Classification via Controlled Image Compositions","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2504.13548","title":"Beyond One-Hot Labels: Semantic Mixing for Model Calibration","created":"2025-04-18","cited_by_count":2,"area":null},{"id":"2505.19495","title":"The Role of Video Generation in Enhancing Data-Limited Action Understanding","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2510.08095","title":"Beyond Real Data: Synthetic Data through the Lens of Regularization","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2510.12060","title":"Your VAR Model is Secretly an Efficient and Explainable Generative Classifier","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2606.00571","title":"On the Difficulty of Learning a Meta-network for Training Data Selection","created":"2026-05-30","cited_by_count":2,"area":null},{"id":"2606.13625","title":"Revisiting Vehicle Color Recognition in Long-Tailed Surveillance Scenarios","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2307.08526","title":"Image Captions are Natural Prompts for Text-to-Image Models","created":"2023-07-17","cited_by_count":1,"area":null},{"id":"2311.01655","title":"Detecting Spurious Correlations via Robust Visual Concepts in Real and AI-Generated Image Classification","created":"2023-11-03","cited_by_count":1,"area":null},{"id":"2311.18332","title":"Multilevel Saliency-Guided Self-Supervised Learning for Image Anomaly Detection","created":"2023-11-30","cited_by_count":1,"area":null},{"id":"2402.09237","title":"Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency","created":"2024-02-14","cited_by_count":1,"area":null},{"id":"2404.12611","title":"Rethinking Clothes Changing Person ReID: Conflicts, Synthesis, and Optimization","created":"2024-04-19","cited_by_count":1,"area":null},{"id":"2405.19590","title":"Weights Augmentation: it has never ever ever ever let her model down","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2406.05923","title":"Contrastive Learning from Synthetic Audio Doppelg\\\"angers","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2409.08181","title":"Enhancing Canine Musculoskeletal Diagnoses: Leveraging Synthetic Image Data for Pre-Training AI-Models on Visual Documentations","created":"2024-09-12","cited_by_count":1,"area":null},{"id":"2411.03098","title":"Local Lesion Generation is Effective for Capsule Endoscopy Image Data Augmentation in a Limited Data Setting","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2412.00684","title":"Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding","created":"2024-12-01","cited_by_count":1,"area":null},{"id":"2412.16227","title":"GALOT: Generative Active Learning via Optimizable Zero-shot Text-to-image Generation","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2501.17690","title":"Segmentation-Aware Generative Reinforcement Network (GRN) for Tissue Layer Segmentation in 3-D Ultrasound Images for Chronic Low-back Pain (cLBP) Assessment","created":"2025-01-29","cited_by_count":1,"area":null},{"id":"2505.04963","title":"ViCTr: Vital Consistency Transfer for Pathology Aware Image Synthesis","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2505.16972","title":"From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2505.20687","title":"VisAlgae 2023: A Dataset and Challenge for Algae Detection in Microscopy Images","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2506.19360","title":"SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2506.23038","title":"Inpainting is All You Need: A Diffusion-based Augmentation Method for Semi-supervised Medical Image Segmentation","created":"2025-06-28","cited_by_count":1,"area":null},{"id":"2507.02217","title":"Understanding Trade offs When Conditioning Synthetic Data","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2507.07077","title":"RulerNet: Learning Perspective-Invariant Ruler Representations for Robust Image Scale Estimation","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2508.07723","title":"Enhancing Small-Scale Dataset Expansion with Triplet-Connection-based Sample Re-Weighting","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2508.09550","title":"Exploring the Equivalence of Closed-Set Generative and Real Data Augmentation in Image Classification","created":"2025-08-13","cited_by_count":1,"area":null}],"next_cursor":"100"}