让时间序列图自动生成领域专属描述，无需重新训练。
TADACap: Time-series Adaptive Domain-Aware Captioning
- 基于检索构建框架，从目标领域数据库找图文对。
- 在金融医疗数据上表现接近顶尖模型，标注成本大幅降低。
- 适合需要快速适配新领域的场景，如医疗监测、股票分析。
尽管图像字幕生成已受广泛关注，但金融、医疗等领域常见的时间序列图像的字幕生成潜力仍未被充分挖掘。现有方法通常提供通用、不区分领域的时序形状描述，且难以在不经过大量重训练的情况下适应新领域。为此，我们提出 TADACap，一种基于检索的框架，可生成针对特定领域的时序图像字幕，并支持在不重新训练的前提下适应新领域。在此基础上，我们进一步提出 TADACap-diverse，一种从目标领域数据库中检索多样图文对的新策略。我们在多个基准上对比了 TADACap-diverse 与先进方法及消融变体，结果表明其在语义准确性上表现相当，同时显著减少标注需求。
原文摘要 · Abstract (English)
While image captioning has gained significant attention, the potential of captioning time-series images, prevalent in areas like finance and healthcare, remains largely untapped. Existing time-series captioning methods typically offer generic, domain-agnostic descriptions of time-series shapes and struggle to adapt to new domains without substantial retraining. To address these limitations, we introduce TADACap, a retrieval-based framework to generate domain-aware captions for time-series images, capable of adapting to new domains without retraining. Building on TADACap, we propose a novel retrieval strategy that retrieves diverse image-caption pairs from a target domain database, namely TADACap-diverse. We benchmarked TADACap-diverse against state-of-the-art methods and ablation variants. TADACap-diverse demonstrates comparable semantic accuracy while requiring significantly less annotation effort.
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。