素描
零(语言学)
人工智能
图像检索
公制(单位)
计算机科学
弹丸
图像(数学)
关系(数据库)
计算机视觉
模式识别(心理学)
数学
算法
数据挖掘
语言学
哲学
运营管理
化学
有机化学
经济
作者
Yang Liu,Yuhao Dang,Xinbo Gao,Jungong Han,Ling Shao
标识
DOI:10.1016/j.patcog.2024.110452
摘要
Retrieving natural images with the query sketches under the zero-shot scenario is known as zero-shot sketch-based image retrieval (ZS-SBIR). Most of the best-performing methods adapt the triplet loss to learn projections that map natural images and sketches to a latent embedding space. They nevertheless neglect the modality gap between the hand-drawn sketches and the photos and consider no difference between any two incorrect classes, which limits their performance in real use cases. Towards this end, we put forward a simple and effective model, which adopts relation-aware metric learning to suppress the modality gap between the sketches and the photos. We also propose an adaptive margin that utilizes each anchor in embedding space to improves clustering ability in metric learning. Extensive experiments on the Sketchy and TU-Berlin datasets show the dominant position of our proposed model over SOTA competitors.
科研通智能强力驱动
Strongly Powered by AbleSci AI