ASMR: Learning Attribute-based Person Search With Adaptive Semantic Margin Regularizer

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 emb

Stats

• citations21
• S2 citations—
• github stars0
• HF likes0
• heat score10.07
• arxiv keyjeong2021asmr

Related papers

• Symbiotic Adversarial Learning For Attribute-based Person Search (2020)13.04
• Improving Text-based Person Search Via Part-level Cross-modal Correspondence (2024)0.00
• Multi-attribute Enhancement Network For Person Search (2021)7.84
• Learning Context-aware Embedding For Person Search (2021)0.00
• Improving Video Retrieval By Adaptive Margin (2023)9.92
• Multi-path Exploration And Feedback Adjustment For Text-to-image Person Retrieval (2024)0.00
• Preserving Semantic Neighborhoods For Robust Cross-modal Retrieval (2020)10.07
• Large Margin Learning In Set To Set Similarity Comparison For Person Re-identification (2017)12.10