并非每个 Patch 都是必需的：面向基于视频的行人重识别的更高效且更有效的骨干网络
Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification
AI总结：
本文提出一种面向基于视频的行人重识别的高效骨干网络，通过引入 patch 选择机制和伪帧全局上下文，在大幅降低计算成本的同时保持或提升了识别准确率。
摘要：
本文提出了一种用于基于视频的行人重识别（ReID）的新型高效即插即用骨干网络。传统基于视频的 ReID 方法通常使用 CNN 或 transformer 骨干网络对每个采样视频帧中的每个位置提取深度特征。在此我们认为这种穷举式特征提取是不必要的，因为我们发现 ReID 视频中的不同帧通常差异较小，且由于人类的轻微动作而包含许多相似区域。受此启发，本文探索了一种更具选择性、更高效的范式。具体而言，我们引入了 patch 选择机制，通过仅选择关键且非重复的 patch 进行特征提取来降低计算成本。此外，我们提出了一种新颖的网络结构，用于生成并利用伪帧全局上下文，以解决由稀疏输入导致的视角不完整问题。通过引入这些新设计，我们的骨干网络能够同时实现高性能和低计算成本。在多个数据集上的大量实验表明，与 ViT-B 相比，我们的方法将计算成本降低了 74%，与 ResNet50 相比降低了 28%，同时准确率与 ViT-B 持平，并显著优于 ResNet50。
英文摘要：
This paper proposes a new effective and efficient plug-and-play backbone for video-based person re-identification (ReID). Conventional video-based ReID methods typically use CNN or transformer backbones to extract deep features for every position in every sampled video frame. Here, we argue that this exhaustive feature extraction could be unnecessary, since we find that different frames in a ReID video often exhibit small differences and contain many similar regions due to the relatively slight movements of human beings. Inspired by this, a more selective, efficient paradigm is explored in this paper. Specifically, we introduce a patch selection mechanism to reduce computational cost by choosing only the crucial and non-repetitive patches for feature extraction. Additionally, we present a novel network structure that generates and utilizes pseudo frame global context to address the issue of incomplete views resulting from sparse inputs. By incorporating these new designs, our backbone can achieve both high performance and low computational cost. Extensive experiments on multiple datasets show that our approach reduces the computational cost by 74\% compared to ViT-B and 28\% compared to ResNet50, while the accuracy is on par with ViT-B and outperforms ResNet50 significantly.
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。
