Query-guided networks for few-shot fine-grained classification and person search

• Published in: Pattern recognition Vol. 133; p. 109049
• Main Authors: Munjal, Bharti, Flaborea, Alessandro, Amin, Sikandar, Tombari, Federico, Galasso, Fabio
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.01.2023
• Subjects: Few-shot learning; Fine-grained classification; Meta-learning; Person re-identification; Person search; Few-shot learning; Person re-identification; Meta-learning; Fine-grained classification; Person search
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2022.109049

•Prior works treat few-shot fine-grained classification and person search separately.•The proposed query-guided networks (QGN) address both tasks in a unified framework.•QGN introduces query-guidance for the task of few-shot fine-grained recognition.•State-of-the-art performance on CUB, FGVC-Aircraft, Stanford Dogs datasets.•The paper performs an in-depth analysis of each of the query-guided components of QGN. [Display omitted] Few-shot fine-grained classification and person search appear as distinct tasks and literature has treated them separately. But a closer look unveils important similarities: both tasks target categories that can only be discriminated by specific object details; and the relevant models should generalize to new categories, not seen during training. We propose a novel unified Query-Guided Network (QGN) applicable to both tasks. QGN consists of a Query-guided Siamese-Squeeze-and-Excitation subnetwork which re-weights both the query and gallery features across all network layers, a Query-guided Region Proposal subnetwork for query-specific localisation, and a Query-guided Similarity subnetwork for metric learning. QGN improves on a few recent few-shot fine-grained datasets, outperforming other techniques on CUB by a large margin. QGN also performs competitively on the person search CUHK-SYSU and PRW datasets, where we perform in-depth analysis.