Scholarlink

This study presents a lightweight image retrieval system for a domain-specific dataset. The proposed system employs a Vision Transformer (ViT) with multi-head attention [1] to learn visual representations from a product image dataset collected from the Vietnamese e-commerce platforms. The model was trained entirely from scratch. The image feature vectors are stored and indexed in Qdrant to enable efficient similarity search. Experimental results indicate that the proposed approach provides improved clustering performance across several baseline models under our evaluation setting, while requiring fewer parameters.

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

Lightweight ViT-Based Image Retrieval System with Qdrant for Efficient Similarity Search

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Pham Tran Nhat Linh,
  • Ngo Thanh Hung,
  • Ngo Phuoc Dai,
  • Hoang Le Viet Ha,
  • Le Thi Thuy Linh,
  • Tran Thao Dung,
  • Huynh Thanh Viet

摘要

This study presents a lightweight image retrieval system for a domain-specific dataset. The proposed system employs a Vision Transformer (ViT) with multi-head attention [1] to learn visual representations from a product image dataset collected from the Vietnamese e-commerce platforms. The model was trained entirely from scratch. The image feature vectors are stored and indexed in Qdrant to enable efficient similarity search. Experimental results indicate that the proposed approach provides improved clustering performance across several baseline models under our evaluation setting, while requiring fewer parameters.