no code implementations • 16 Feb 2023 • Jinkuan Zhu, Hao Huang, Qiao Deng, Xiyao Li
In this paper, we propose a novel fashion image retrieval method leveraging both global and fine-grained features, dubbed Multi-Granular Alignment (MGA).
Ranked #3 on Metric Learning on In-Shop
1 code implementation • 17 Nov 2022 • Pengpeng Zeng, Jinkuan Zhu, Jingkuan Song, Lianli Gao
Specifically, we design a novel embedding method called tree-structured prototype, producing a set of hierarchical representative embeddings which capture the hierarchical semantic structure in textual space.