View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification

TL;DR

This paper introduces ViSA, a view-aware semantic alignment framework for aerial-ground person re-identification, effectively handling viewpoint variations with innovative modules and achieving superior benchmark performance.

Contribution

Proposes ViSA, a novel view-aware framework with expert-driven token generation and local fusion modules for improved cross-view person re-identification.

Findings

Achieves a 10.06% mAP improvement on CARGO benchmark.

Demonstrates superior performance across three AGPReID datasets.

Effectively models viewpoint-specific cues with new modules.

Abstract

Aerial-Ground Person Re-Identification (AGPReID) remains highly challenging due to drastic viewpoint variations between drones and fixed cameras. Existing methods typically follow a view-invariant paradigm, aligning shared features across views to achieve robustness. However, view-invariant inherently enforces part-level alignment, which ignores view-specific cues and discriminative identity information. To this end, this work proposes ViSA (View-aware Semantic Alignment), a view-aware framework that achieves cross-view semantic consistency containing an Expert-driven Token Generation Module (ETGM) and a Dual-branch Local Fusion Module (DLFM). Technically, the former constructs a set of view-aware experts to generate adaptive semantic queries that perceive viewpoint-specific patterns, while the latter leverages graph reasoning to extract and align local regions responsive to different experts. Extensive experiments on three AGPReID benchmarks including AG-ReID.v2, CARGO and LAGPeR demonstrate that ViSA consistently achieves superior performance, with a notable 10.06\% mAP improvement on the challenging CARGO cross-view protocol. The code is available at \href{https://github.com/Cat-Zero/ViSA}{https://github.com/Cat-Zero/ViSA}.