Symbiotic Adversarial Learning For Attribute-based Person Search

Abstract

Attribute-based person search is in significant demand for applications where no detected query images are available, such as identifying a criminal from witness. However, the task itself is quite challenging because there is a huge modality gap between images and physical descriptions of attributes. Often, there may also be a large number of unseen categories (attribute combinations). The current state-of-the-art methods either focus on learning better cross-modal embeddings by mining only seen data, or they explicitly use generative adversarial networks (GANs) to synthesize unseen features. The former tends to produce poor embeddings due to insufficient data, while the latter does not preserve intra-class compactness during generation. In this paper, we present a symbiotic adversarial learning framework, called SAL.Two GANs sit at the base of the framework in a symbiotic learning scheme: one synthesizes features of unseen classes/categories, while the other optimizes the embedding an

Stats

• citations23
• S2 citations—
• github stars21
• HF likes0
• heat score13.04
• arxiv keycao2020symbiotic

Related papers

• ASMR: Learning Attribute-based Person Search With Adaptive Semantic Margin Regularizer (2021)10.07
• Multi-attribute Enhancement Network For Person Search (2021)7.84
• Effectively Leveraging Attributes For Visual Similarity (2021)3.66
• Improving Text-based Person Search Via Part-level Cross-modal Correspondence (2024)0.00
• Contrastive Transformer Learning With Proximity Data Generation For Text-based Person Search (2023)11.88
• Self-supervised Adversarial Hashing Networks For Cross-modal Retrieval (2018)19.56
• Learning Context-aware Embedding For Person Search (2021)0.00
• Unsupervised Adversarial Attacks On Deep Feature-based Retrieval With GAN (2019)0.00