用自然语言指导图像聚类，让结果更符合用户意图。
Interpretable Text-Guided Image Clustering via Iterative Search
- 通过迭代搜索生成可解释的视觉概念，匹配用户语言指令。
- 在多个图像聚类与细粒度分类任务中表现优于现有方法。
- 适合需要语义可控聚类的科研与实际应用人员。
传统聚类方法仅基于数据点间的相似性进行分组，但在缺乏额外信息时存在多解问题，不同用户可能依据形状、颜色等不同标准划分同一数据集。近期提出的文本引导图像聚类方法通过自然语言指令提供上下文和控制，使聚类结果更贴近用户意图。本文提出一种名为ITGC的新方法，采用由无监督聚类目标引导的迭代发现过程，生成能更好捕捉用户指令中语义准则的可解释视觉概念。实验表明，该方法在广泛覆盖的图像聚类与细粒度分类基准上均取得优于现有方法的性能。
原文摘要 · Abstract (English)
Traditional clustering methods aim to group unlabeled data points based on their similarity to each other. However, clustering, in the absence of additional information, is an ill-posed problem as there may be many different, yet equally valid, ways to partition a dataset. Distinct users may want to use different criteria to form clusters in the same data, e.g. shape v.s. color. Recently introduced text-guided image clustering methods aim to address this ambiguity by allowing users to specify the criteria of interest using natural language instructions. This instruction provides the necessary context and control needed to obtain clusters that are more aligned with the users' intent. We propose a new text-guided clustering approach named ITGC that uses an iterative discovery process, guided by an unsupervised clustering objective, to generate interpretable visual concepts that better capture the criteria expressed in a user's instructions. We report superior performance compared to existing methods across a wide variety of image clustering and fine-grained classification benchmarks.
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。