低秩引导视觉语言模型的非参数深度细粒度聚类
Nonparametric Deep Fine-grained Clustering with Low-Rank Guided Vision-Language Model
把贝叶斯非参数过程与低秩/正交引导的表征学习目标结合，可在无细粒度标签下让 VLM 动态发现细粒度类别，为无监督细粒度分类与聚类提供可复用的训练目标设计。
原文依据 integrating a Bayesian nonparametric process with a tailored representation learning objective, which includes low-rank guidance and orthogonal guidance
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论标注细粒度数据的稀缺为深度聚类带来了显著挑战。现有粗粒度数据集（具有类间方差大、类内方差小的特点）上的视觉语言模型难以捕捉细粒度分类所必需的细微差异，导致聚类性能欠佳。为解决这一问题，我们提出了一种新框架，使视觉语言模型无需细粒度标签即可适配细粒度聚类。该方法通过将贝叶斯非参数过程与定制的表征学习目标相结合，引导模型关注具有判别性的细粒度特征，该目标包含低秩引导与正交引导。由此，我们的模型能够动态发现反映细粒度类别的簇。大量实验表明，该方法在多个细粒度基准上取得了最优性能。代码见 https://github.com/HenryWells02/VLM-Fine-Clustering。
英文原文摘要 1017 字符
The scarcity of labeled fine-grained data presents a significant challenge for deep clustering. Vision-Language Models (VLMs) on existing coarse-grained datasets (characterized by high inter-class and low intra-class variance) struggle to capture the subtle distinctions essential for fine-grained categorization, leading to suboptimal clustering performance. To address this, we propose a novel framework that adapts VLMs for fine-grained clustering without requiring fine-grained labels. Our method steers the model to focus on discriminative fine-grained features by integrating a Bayesian nonparametric process with a tailored representation learning objective, which includes low-rank guidance and orthogonal guidance. This allows our model to dynamically discover clusters that reflect fine-grained categories. Extensive experiments demonstrate that our approach achieves state-of-the-art performance on multiple fine-grained benchmarks. Code is available at https://github.com/HenryWells02/VLM-Fine-Clustering.