Abstract
Aerial-Ground person Re-IDentification (AG-ReID) aims to retrieve specific persons across heterogeneous cameras in different views. Previous methods usually adopt large-scale models, focusing on view-invariant features. However, they overlook the semantic information in person attributes. Additionally, existing training strategies often rely on full fine-tuning large-scale models, which significantly increases training costs. To address these issues, we propose a novel framework named LATex for AG-ReID, which adopts prompt-tuning strategies to leverage attribute-based text knowledge. More specifically, we first introduce the Contrastive Language-Image Pre-training (CLIP) model as the backbone, and propose an Attribute-aware Image Encoder (AIE) to extract global semantic features and attribute-aware features. Then, with these features, we propose a Prompted Attribute Classifier Group (PACG) to generate person attribute predictions and obtain the encoded representations of predicted attributes. Finally, we design a Coupled Prompt Template (CPT) to transform attribute tokens and view information into structured sentences. These sentences are processed by the text encoder of CLIP to generate more discriminative features. As a result, our framework can fully leverage attribute-based text knowledge to improve the AG-ReID. Extensive experiments on three AG-ReID benchmarks demonstrate the effectiveness of our proposed LATex. The source code will be available.
Abstract (translated)
空中-地面人员重识别（AG-ReID）旨在检索跨不同视角中异构摄像机中的特定人员。以往的方法通常采用大规模模型，专注于视图不变特征。然而，它们忽略了人体属性中的语义信息。此外，现有的训练策略往往依赖于对大规模模型进行完全微调，这大大增加了训练成本。为了解决这些问题，我们提出了一种名为LATex的新框架用于AG-ReID，该框架采用了提示微调策略以利用基于属性的文本知识。 更具体地说，首先我们将对比语言图像预训练（CLIP）模型作为骨干网络，并提出了一个感知属性的图像编码器（AIE），用于提取全局语义特征和感知属性的特征。然后，利用这些特征，我们提出了一种提示属性分类器组（PACG）以生成人员属性预测并获取预测属性的编码表示。最后，我们设计了一个耦合提示模板（CPT）将属性标记和视图信息转换为结构化句子。这些句子通过CLIP中的文本编码器处理，从而产生更具判别性的特征。 因此，我们的框架可以充分利用基于属性的文本知识以改进AG-ReID性能。在三个AG-ReID基准数据集上的广泛实验展示了我们提出的LATex的有效性。源代码将公开提供。
URL
https://arxiv.org/abs/2503.23722
