用任务感知选样提升遥感图像多标注表示学习效果
Task-Guided Multi-Annotation Triplet Learning for Remote Sensing Representations
- 根据互信息筛选跨任务最有效的三元组样本
- 在野生动物航拍数据集上分类与回归性能均提升
- 适合需要多任务协同的遥感图像表征学习场景
先前的多任务三元组损失方法依赖静态权重来平衡不同标注类型间的监督信号，但静态权重需调参且无法反映任务间交互对共享表示的影响。为此，本文提出任务引导的多标注三元组损失，通过互信息准则选择跨任务最具信息量的三元组，从而决定哪些样本影响表示学习，而非调整损失大小。在航空野生动物数据集上的实验表明，该方法相比多种三元组损失设置，在多任务表示学习中表现更优，显著提升了分类与回归性能，验证了任务感知三元组选择能生成更有效的共享表示。
原文摘要 · Abstract (English)
Prior multi-task triplet loss methods relied on static weights to balance supervision between various types of annotation. However, static weighting requires tuning and does not account for how tasks interact when shaping a shared representation. To address this, the proposed task-guided multi-annotation triplet loss removes this dependency by selecting triplets through a mutual-information criteria that identifies triplets most informative across tasks. This strategy modifies which samples influence the representation rather than adjusting loss magnitudes. Experiments on an aerial wildlife dataset compare the proposed task-guided selection against several triplet loss setups for shaping a representation in an effective multi-task manner. The results show improved classification and regression performance and demonstrate that task-aware triplet selection produces a more effective shared representation for downstream tasks.
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。