Query-Guided Networks for Few-shot Fine-grained Classification and Person Search

TL;DR

This paper introduces a unified Query-Guided Network (QGN) that effectively handles both few-shot fine-grained classification and person search by leveraging query-guided feature re-weighting, localization, and similarity learning.

Contribution

The paper presents a novel unified network architecture that applies query-guided mechanisms to both tasks, improving performance on fine-grained and person search datasets.

Findings

QGN outperforms recent methods on CUB dataset

QGN achieves competitive results on CUHK-SYSU and PRW datasets

Query-guided modules enhance feature discrimination and localization

Abstract

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.