SGD-Mix：利用标签保持数据增强增强特定领域图像分类
SGD-Mix: Enhancing Domain-Specific Image Classification with Label-Preserving Data Augmentation
AI总结：
针对特定领域图像分类中增强数据多样性、真实性与标签清晰度难以兼顾的问题，提出SGD-Mix框架，结合显著性引导混合和微调扩散模型，并在多类任务上验证其优于现有方法。
摘要：
面向特定领域图像分类任务的数据增强往往难以同时兼顾生成数据的多样性、真实性和标签清晰度，从而导致下游任务性能欠佳。尽管现有基于生成式扩散模型的方法旨在增强数据增强，但它们未能协同解决这三个关键方面，并且常常忽视扩散模型的内在挑战，例如对模型特性的敏感性以及强变换下的随机性。本文提出一种新颖框架，将多样性、真实性和标签清晰度显式整合到增强过程中。该方法采用显著性引导混合与微调扩散模型，以保持前景语义、丰富背景多样性并确保标签一致性，同时缓解扩散模型的局限。在细粒度、长尾、少样本和背景鲁棒性任务上的大量实验表明，该方法性能优于现有最先进方法。
英文摘要：
Data augmentation for domain-specific image classification tasks often struggles to simultaneously address diversity, faithfulness, and label clarity of generated data, leading to suboptimal performance in downstream tasks. While existing generative diffusion model-based methods aim to enhance augmentation, they fail to cohesively tackle these three critical aspects and often overlook intrinsic challenges of diffusion models, such as sensitivity to model characteristics and stochasticity under strong transformations. In this paper, we propose a novel framework that explicitly integrates diversity, faithfulness, and label clarity into the augmentation process. Our approach employs saliency-guided mixing and a fine-tuned diffusion model to preserve foreground semantics, enrich background diversity, and ensure label consistency, while mitigating diffusion model limitations. Extensive experiments across fine-grained, long-tail, few-shot, and background robustness tasks demonstrate our method's superior performance over state-of-the-art approaches.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
