解决遥感图像多标签检索中的类别不平衡问题
MARC: Multi-Label Adaptive Retrieval Contrastive Loss for Remote Sensing Images
- 设计自适应对比学习框架，融合标签感知采样与动态温度调节
- 在三个基准数据集上优于基线模型，显著提升稀有类别的检索准确率
- 适合遥感图像检索、土地覆盖分析等需要处理复杂类间共现的应用
土地覆盖类别间语义重叠、标签分布高度不均衡以及复杂的类别共现模式，是多标签遥感图像检索面临的主要挑战。本文提出多标签自适应对比学习（MACL），作为对比学习的扩展，通过引入标签感知采样、频率敏感加权和动态温度缩放，实现对常见与罕见类别的一致表征学习。在DLRSD、ML-AID和WHDLD三个基准数据集上的大量实验表明，MACL持续优于基于对比损失的基线方法，有效缓解语义不平衡问题，在大规模遥感图像档案中提供更可靠的检索性能。代码、预训练模型及评估脚本将在论文接收后公开于https://github.com/Amna-128/MARC。
原文摘要 · Abstract (English)
Semantic overlap among land-cover categories, highly imbalanced label distributions, and complex inter-class co-occurrence patterns constitute significant challenges for multi-label remote-sensing image retrieval. In this article, Multi-Label Adaptive Contrastive Learning (MACL) is introduced as an extension of contrastive learning to address them. It integrates label-aware sampling, frequency-sensitive weighting, and dynamic-temperature scaling to achieve balanced representation learning across both common and rare categories. Extensive experiments on three benchmark datasets (DLRSD, ML-AID, and WHDLD), show that MACL consistently outperforms contrastive-loss based baselines, effectively mitigating semantic imbalance and delivering more reliable retrieval performance in large-scale remote-sensing archives. Code, pretrained models, and evaluation scripts will be released at https://github.com/Amna-128/MARC upon acceptance.
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。