Abstract
Visible-Infrared Person Re-identification (VI-ReID) is a challenging cross-modal pedestrian retrieval task, due to significant intra-class variations and cross-modal discrepancies among different cameras. Existing works mainly focus on embedding images of different modalities into a unified space to mine modality-shared features. They only seek distinctive information within these shared features, while ignoring the identity-aware useful information that is implicit in the modality-specific features. To address this issue, we propose a novel Implicit Discriminative Knowledge Learning (IDKL) network to uncover and leverage the implicit discriminative information contained within the modality-specific. First, we extract modality-specific and modality-shared features using a novel dual-stream network. Then, the modality-specific features undergo purification to reduce their modality style discrepancies while preserving identity-aware discriminative knowledge. Subsequently, this kind of implicit knowledge is distilled into the modality-shared feature to enhance its distinctiveness. Finally, an alignment loss is proposed to minimize modality discrepancy on enhanced modality-shared features. Extensive experiments on multiple public datasets demonstrate the superiority of IDKL network over the state-of-the-art methods. Code is available at this https URL.
Abstract (translated)
可见-红外人物识别（VI-ReID）是一个具有挑战性的跨模态行人检索任务，因为不同相机之间存在显著的类内差异和跨模态差异。现有工作主要集中在将不同模态的图像嵌入到一个统一的 space 中，以挖掘模态共性特征。他们仅关注这些共享特征中的显着信息，而忽略了隐含在模态特定特征中的身份意识有用信息。为了解决这个问题，我们提出了一个新颖的隐式区分性知识学习（IDKL）网络来揭示和利用模态特定特征中隐含的区分性信息。首先，我们使用一种新颖的双流网络提取模态特定和模态共性特征。然后，模态特定特征经过净化，以减少其模态风格差异，同时保留身份意识区分性知识。接下来，这种隐含知识被蒸馏到模态共性特征中，以增强其独特性。最后，提出了一种对增强模态共性特征的同步损失，以最小化模态差异。在多个公开数据集上进行的大量实验证明，IDKL网络相对于最先进的方法具有优越性。代码可在此链接处获取。
URL
https://arxiv.org/abs/2403.11708
