通过前后景分域增强，减少对标注数据依赖
Effective Dual-Region Augmentation for Reduced Reliance on Large Amounts of Labeled Data
- 对前景加噪声、背景拼贴，提升数据多样性
- PACS上跨域适应准确率超现有方法，多目标场景提升显著
- 适合小样本或标注成本高的视觉任务
本文提出一种新型双区域增强方法，旨在降低对大规模标注数据的依赖，同时提升模型在多种计算机视觉任务中的鲁棒性和适应性，涵盖源无域适应（SFDA）和行人重识别（ReID）。该方法通过对前景对象施加随机噪声扰动，并对背景块进行空间混洗，有效增加训练数据的多样性，从而提升模型鲁棒性与泛化能力。在PACS数据集上的SFDA评估显示，该增强策略在单目标和多目标适应设置下均显著优于现有方法，实现明显准确率提升。通过结构化变换增强训练数据，本方法实现了跨域泛化，为减少人工标注依赖提供了可扩展解决方案。此外，在Market-1501和DukeMTMC-reID数据集上的实验验证了其在行人ReID任务中的有效性，性能超越传统增强技术。
原文摘要 · Abstract (English)
This paper introduces a novel dual-region augmentation approach designed to reduce reliance on large-scale labeled datasets while improving model robustness and adaptability across diverse computer vision tasks, including source-free domain adaptation (SFDA) and person re-identification (ReID). Our method performs targeted data transformations by applying random noise perturbations to foreground objects and spatially shuffling background patches. This effectively increases the diversity of the training data, improving model robustness and generalization. Evaluations on the PACS dataset for SFDA demonstrate that our augmentation strategy consistently outperforms existing methods, achieving significant accuracy improvements in both single-target and multi-target adaptation settings. By augmenting training data through structured transformations, our method enables model generalization across domains, providing a scalable solution for reducing reliance on manually annotated datasets. Furthermore, experiments on Market-1501 and DukeMTMC-reID datasets validate the effectiveness of our approach for person ReID, surpassing traditional augmentation techniques. The code is available at https://github.com/PrasannaPulakurthi/Foreground-Background-Augmentation
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。