An efficient framework for zero-shot sketch-based image retrieval

作者：

Highlights：

• We propose an efficient framework for zero-shot sketch-based image retrieval.

• The model is trained in an end-to-end way with three introduced learning objectives: domain-balanced quadruplet loss, semantic classification loss and semantic knowledge preservation loss.

• A low-cost but accurate semantic knowledge distillation pipeline is introduced. It does not require a language model or an online teacher network as with past approaches.

• The proposed method achieved state-of-the-art results on three challenging zero-shot sketch-based image retrieval datasets: Sketchy Extended, TU-Berlin Extended and QuickDraw Extended.

摘要

•We propose an efficient framework for zero-shot sketch-based image retrieval.•The model is trained in an end-to-end way with three introduced learning objectives: domain-balanced quadruplet loss, semantic classification loss and semantic knowledge preservation loss.•A low-cost but accurate semantic knowledge distillation pipeline is introduced. It does not require a language model or an online teacher network as with past approaches.•The proposed method achieved state-of-the-art results on three challenging zero-shot sketch-based image retrieval datasets: Sketchy Extended, TU-Berlin Extended and QuickDraw Extended.

论文关键词：Sketch-based image retrieval,Zero-shot learning,Knowledge distillation,Similarity learning

论文评审过程：Received 26 January 2021, Revised 14 November 2021, Accepted 9 January 2022, Available online 21 January 2022, Version of Record 2 February 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108528