面向视频行人重识别的深度耦合卷积-Transformer时空互补学习
Deeply-Coupled Convolution-Transformer with Spatial-temporal Complementary Learning for Video-based Person Re-identification
AI总结：
针对视频行人重识别中CNN全局表征不足的问题，提出深度耦合卷积-Transformer时空互补学习框架，结合空间互补注意力、层次时间聚合与自蒸馏策略，在多个基准上取得优于多数现有方法的性能。
摘要：
先进的深度卷积神经网络（CNNs）已在视频行人重识别（Re-ID）领域取得显著成效，但这类网络通常聚焦于行人最显眼的区域，全局表征能力有限。近年研究表明，Transformer可通过全局感知探索图像块间的关联，从而提升性能。本文结合二者优势，提出一种新型时空互补学习框架——深度耦合卷积-Transformer（DCCT），用于实现高性能的视频行人重识别。首先，本文将CNNs与Transformer耦合，提取两类视觉特征，并通过实验验证了二者的互补性。在空间维度，提出互补内容注意力（CCA），利用耦合结构引导独立特征完成空间互补学习；在时间维度，提出层次化时间聚合（HTA），逐步捕捉帧间依赖关系并编码时间信息，同时采用门控注意力将聚合后的时间信息传递至CNN和Transformer分支，实现时间互补学习。最后，引入自蒸馏训练策略，将更优的时空知识迁移至骨干网络，以提升准确率与效率。通过该机制，同一视频的两类典型特征被有机整合，形成信息更丰富的表征。在四个公开Re-ID基准上的大量实验表明，本文框架的性能优于多数现有最优方法。
英文摘要：
Advanced deep Convolutional Neural Networks (CNNs) have shown great success in video-based person Re-Identification (Re-ID). However, they usually focus on the most obvious regions of persons with a limited global representation ability. Recently, it witnesses that Transformers explore the inter-patch relations with global observations for performance improvements. In this work, we take both sides and propose a novel spatial-temporal complementary learning framework named Deeply-Coupled Convolution-Transformer (DCCT) for high-performance video-based person Re-ID. Firstly, we couple CNNs and Transformers to extract two kinds of visual features and experimentally verify their complementarity. Further, in spatial, we propose a Complementary Content Attention (CCA) to take advantages of the coupled structure and guide independent features for spatial complementary learning. In temporal, a Hierarchical Temporal Aggregation (HTA) is proposed to progressively capture the inter-frame dependencies and encode temporal information. Besides, a gated attention is utilized to deliver aggregated temporal information into the CNN and Transformer branches for temporal complementary learning. Finally, we introduce a self-distillation training strategy to transfer the superior spatial-temporal knowledge to backbone networks for higher accuracy and more efficiency. In this way, two kinds of typical features from same videos are integrated mechanically for more informative representations. Extensive experiments on four public Re-ID benchmarks demonstrate that our framework could attain better performances than most state-of-the-art methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
