English

ASMR: Learning Attribute-Based Person Search with Adaptive Semantic Margin Regularizer

Computer Vision and Pattern Recognition 2021-08-12 v1 Artificial Intelligence Machine Learning

Abstract

Attribute-based person search is the task of finding person images that are best matched with a set of text attributes given as query. The main challenge of this task is the large modality gap between attributes and images. To reduce the gap, we present a new loss for learning cross-modal embeddings in the context of attribute-based person search. We regard a set of attributes as a category of people sharing the same traits. In a joint embedding space of the two modalities, our loss pulls images close to their person categories for modality alignment. More importantly, it pushes apart a pair of person categories by a margin determined adaptively by their semantic distance, where the distance metric is learned end-to-end so that the loss considers importance of each attribute when relating person categories. Our loss guided by the adaptive semantic margin leads to more discriminative and semantically well-arranged distributions of person images. As a consequence, it enables a simple embedding model to achieve state-of-the-art records on public benchmarks without bells and whistles.

Keywords

Cite

@article{arxiv.2108.04533,
  title  = {ASMR: Learning Attribute-Based Person Search with Adaptive Semantic Margin Regularizer},
  author = {Boseung Jeong and Jicheol Park and Suha Kwak},
  journal= {arXiv preprint arXiv:2108.04533},
  year   = {2021}
}

Comments

ICCV 2021 accepted

R2 v1 2026-06-24T04:58:54.143Z