用少量多标签图像实现高效自监督表示学习
Self-Supervised Contrastive Learning for Multi-Label Images
- 设计块级增强模块，从多标签图像中挖掘更多正样本对
- 提出图像感知对比损失，提升语义一致性表征能力
- 适合数据量少但标签复杂的下游任务场景
自监督学习在通过对比方法学习表征方面表现出色，但主流方法依赖大规模单标签数据集（如ImageNet），导致预训练成本过高。同时，多标签图像虽蕴含更丰富的语义信息且在下游任务中更具适用性，却常被忽略。为此，本文针对多标签图像优化主流自监督学习框架，在较少样本条件下仍能实现优异的表示学习性能。首先提出块级增强模块，从多标签图像中提取额外潜在正样本对；随后设计图像感知对比损失，建立这些视图间的关联，促进语义一致表征的提取。线性微调与迁移学习实验验证了该方法在样本质量与数量有限情况下的竞争力。
原文摘要 · Abstract (English)
Self-supervised learning (SSL) has demonstrated its effectiveness in learning representations through comparison methods that align with human intuition. However, mainstream SSL methods heavily rely on high body datasets with single label, such as ImageNet, resulting in intolerable pre-training overhead. Besides, more general multi-label images are frequently overlooked in SSL, despite their potential for richer semantic information and broader applicability in downstream scenarios. Therefore, we tailor the mainstream SSL approach to guarantee excellent representation learning capabilities using fewer multi-label images. Firstly, we propose a block-wise augmentation module aimed at extracting additional potential positive view pairs from multi-label images. Subsequently, an image-aware contrastive loss is devised to establish connections between these views, thereby facilitating the extraction of semantically consistent representations. Comprehensive linear fine-tuning and transfer learning validate the competitiveness of our approach despite challenging sample quality and quantity.
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。