Scholarlink

Content-based image retrieval (CBIR) is one of the basic tasks of computer vision. Numerous studies have been conducted, leading to many groundbreaking methods based on deep neural networks and even more recently on vision transformers (ViT). In this article, we propose a new CBIR method based on the original self-distilled with no labels semantic features (DINO), obtained using ViT, and then additionally compressed using the principal and neighbourhood component analysis. We show highly accurate results on non trivial datasets such as Caltech-256, as well as on histopathological scans such as Kather and BreaKHis. Our method freely compares with the best CBIR approaches while having very compact image representations.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Vision Transformer Representations for Efficient Content-Based Image Retrieval

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Stanisław Łażewski,
  • Bogusław Cyganek

摘要

Content-based image retrieval (CBIR) is one of the basic tasks of computer vision. Numerous studies have been conducted, leading to many groundbreaking methods based on deep neural networks and even more recently on vision transformers (ViT). In this article, we propose a new CBIR method based on the original self-distilled with no labels semantic features (DINO), obtained using ViT, and then additionally compressed using the principal and neighbourhood component analysis. We show highly accurate results on non trivial datasets such as Caltech-256, as well as on histopathological scans such as Kather and BreaKHis. Our method freely compares with the best CBIR approaches while having very compact image representations.