Kernel triplet loss for image-text retrieval

Zhengxin Pan, Fangyu Wu*, Bailing Zhang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)


Triplet loss is widely used as the objective function in image-text retrieval tasks. However, as all the triplets are treated equally, triplet loss has a bottleneck problem of slow convergence and other unsatisfactory performances. In this article, we propose solutions by appropriately weighting triplets according to the relative similarities among the training samples. Specifically, we present three weighting functions to assign an appropriate weight for the selected informative triplets to accelerate the convergence. We evaluate our approach on two widely used benchmark datasets: Flickr30k and MSCOCO, with results outperforming the previous methods, which demonstrates its superiority.

Original languageEnglish
Article numbere2093
JournalComputer Animation and Virtual Worlds
Issue number3-4
Publication statusPublished - 13 Jun 2022
Externally publishedYes


  • deep metric learning
  • image-text retrieval
  • kernel triplet loss
  • weighting scheme


Dive into the research topics of 'Kernel triplet loss for image-text retrieval'. Together they form a unique fingerprint.

Cite this