3 accepted papers
Learning a generalizable and comprehensive similarity metric to depict the semantic discrepancies between images is the foundation of many computer vision tasks. While existing methods approach this goal by learning an ensemble of embeddings with diverse objectives, the backbone network still receiv…
The pretrain-finetune paradigm in modern computer vision facilitates the success of self-supervised learning, which tends to achieve better transferability than supervised learning. However, with the availability of massive labeled data, a natural question emerges: how to train a better model with b…
In this paper, we propose a deep compositional metric learning (DCML) framework for effective and generalizable similarity measurement between images. Conventional deep metric learning methods minimize a discriminative loss to enlarge interclass distances while suppressing intraclass variations, whi…