用分层语义对齐提升图像聚类，不需训练就能显著提效。
Hierarchical Semantic Alignment for Image Clustering
- 融合标题级描述与名词级概念构建多粒度语义空间。
- 在ImageNet-1K上准确率提升4.2%，ARI提高2.9%。
- 无需训练，适合资源受限场景下的图像聚类任务。
图像聚类是计算机视觉中的经典问题，旨在将图像划分为不同组别。近期研究利用名词作为外部语义知识以提升聚类性能，但常忽视名词本身的语义模糊性，可能扭曲语义表征并降低聚类质量。为此，我们提出一种分层语义对齐方法（CAE），以无训练方式改进聚类效果。该方法融合两类互补文本语义：标题级描述（体现图像内容的细粒度属性）与名词级概念（代表高层物体类别）。首先从WordNet中选取相关名词，从标题数据集提取描述，构建与图像特征对齐的语义空间；然后通过最优传输将图像特征与选定名词及标题对齐，获得更具区分性的语义空间；最后结合增强后的语义与图像特征进行聚类。在8个数据集上的大量实验表明，该方法有效，尤其在ImageNet-1K上相比当前最优无训练方法，准确率提升4.2%，调整兰德指数（ARI）提升2.9%。
原文摘要 · Abstract (English)
Image clustering is a classic problem in computer vision, which categorizes images into different groups. Recent studies utilize nouns as external semantic knowledge to improve clustering performance. However, these methods often overlook the inherent ambiguity of nouns, which can distort semantic representations and degrade clustering quality. To address this issue, we propose a hierarChical semAntic alignmEnt method for image clustering, dubbed CAE, which improves clustering performance in a training-free manner. In our approach, we incorporate two complementary types of textual semantics: caption-level descriptions, which convey fine-grained attributes of image content, and noun-level concepts, which represent high-level object categories. We first select relevant nouns from WordNet and descriptions from caption datasets to construct a semantic space aligned with image features. Then, we align image features with selected nouns and captions via optimal transport to obtain a more discriminative semantic space. Finally, we combine the enhanced semantic and image features to perform clustering. Extensive experiments across 8 datasets demonstrate the effectiveness of our method, notably surpassing the state-of-the-art training-free approach with a 4.2% improvement in accuracy and a 2.9% improvement in adjusted rand index (ARI) on the ImageNet-1K dataset.
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。