Scholarlink

<p>Over the years, on-the-fly fine-grained sketch-based image retrieval (SBIR) has demonstrated significant potential for real-world applications. However, previous methods rely on weight-sharing and attention mechanisms, which increase the computational load and reduce accuracy. This study enhances feature extraction and task differentiation by eliminating weight sharing, thereby preserving strong feature discriminative power. Our model achieves 82.04% Acc@5 and 92.57% Acc@10 on QMUL-Chair-V2, and 66.37% Acc@5 and 80.78% Acc@10 on QMUL-Shoe-V2, outperforming Bi-LSTM, Multi-granularity and LGRL models, demonstrating improved retrieval performance.</p>

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

Unshared Weight combine with Self-attention at Base model for On-The-Fly Fine-Grained SBIR

  • 期刊论文

  • 发表日期：

    2025年7月23日

查看全文
  • Tuan Nguyen Huu,
  • Quynh Dao Thi Thuy

摘要

Over the years, on-the-fly fine-grained sketch-based image retrieval (SBIR) has demonstrated significant potential for real-world applications. However, previous methods rely on weight-sharing and attention mechanisms, which increase the computational load and reduce accuracy. This study enhances feature extraction and task differentiation by eliminating weight sharing, thereby preserving strong feature discriminative power. Our model achieves 82.04% Acc@5 and 92.57% Acc@10 on QMUL-Chair-V2, and 66.37% Acc@5 and 80.78% Acc@10 on QMUL-Shoe-V2, outperforming Bi-LSTM, Multi-granularity and LGRL models, demonstrating improved retrieval performance.