遮挡行人重识别中的动态特征剪枝与整合
Dynamic Feature Pruning and Consolidation for Occluded Person Re-Identification
AI总结：
针对遮挡行人重识别，提出特征剪枝与整合（FPC）框架，通过稀疏编码器丢弃遮挡相关令牌、多视角匹配及特征整合补偿，在Occluded-Duke上mAP和Rank-1分别提升至少8.6%和6.0%。
摘要：
遮挡行人重识别（ReID）是一个具有挑战性的问题，因为遮挡物会污染特征。现有方法依赖先验知识线索（如人体关键点和语义分割）来解决该问题，但在严重遮挡或遮挡物为其他行人时，这些方法容易失效。本文提出了一种特征剪枝与整合（FPC）框架，以规避显式的人体结构解析。该框架主要由稀疏编码器、多视角特征匹配模块和特征整合解码器组成。具体而言，稀疏编码器仅基于类别令牌注意力内的相关性，丢弃不太重要的图像令牌（这些令牌大多与背景噪声和遮挡物相关）。随后，匹配阶段依靠稀疏编码器产生的保留令牌，通过测量图像级和补丁级组合相似度，在候选集中识别k个最近邻。最后，我们使用特征整合模块，利用识别出的邻居来补偿被剪枝的特征，以恢复关键信息，同时忽略噪声和遮挡的干扰。实验结果表明，我们提出的框架在遮挡、部分和整体ReID数据集上均有效。特别是，在具有挑战性的Occluded-Duke数据集上，我们的方法在mAP和Rank-1准确率上分别至少比现有最优结果高出8.6%和6.0%。
英文摘要：
Occluded person re-identification (ReID) is a challenging problem due to contamination from occluders. Existing approaches address the issue with prior knowledge cues, such as human body key points and semantic segmentations, which easily fail in the presence of heavy occlusion and other humans as occluders. In this paper, we propose a feature pruning and consolidation (FPC) framework to circumvent explicit human structure parsing. The framework mainly consists of a sparse encoder, a multi-view feature mathcing module, and a feature consolidation decoder. Specifically, the sparse encoder drops less important image tokens, mostly related to background noise and occluders, solely based on correlation within the class token attention. Subsequently, the matching stage relies on the preserved tokens produced by the sparse encoder to identify k-nearest neighbors in the gallery by measuring the image and patch-level combined similarity. Finally, we use the feature consolidation module to compensate pruned features using identified neighbors for recovering essential information while disregarding disturbance from noise and occlusion. Experimental results demonstrate the effectiveness of our proposed framework on occluded, partial, and holistic Re-ID datasets. In particular, our method outperforms state-of-the-art results by at least 8.6\% mAP and 6.0\% Rank-1 accuracy on the challenging Occluded-Duke dataset.
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。
