MetaGait：学习学习用于步态识别的全样本自适应表征
MetaGait: Learning to Learn an Omni Sample Adaptive Representation for Gait Recognition
AI总结：
本文提出 MetaGait，通过元知识驱动的注意力与时间聚合学习全样本自适应步态表征，在 CASIA-B 和 OU-MVLP 上达到最先进水平。
摘要：
步态识别旨在通过行走模式识别个体，近年来吸引了越来越多的研究关注。然而，步态识别仍受制于轮廓有限的二值视觉线索与大量尺度多样的协变量之间的冲突，这给模型的适应性带来了挑战。本文中，我们通过开发一种新颖的 MetaGait 来解决这一冲突，该方法学习学习一种全样本自适应表征。为实现这一目标，MetaGait 将可引导模型感知样本特定属性的元知识注入注意力机制的校准网络，从全尺度、全维度和全过程视角提升适应性。具体而言，我们在整个过程中利用元知识，分别提出 Meta Triple Attention 和 Meta Temporal Pooling，以同时自适应地捕获来自空间/通道/时间维度的全尺度依赖，并通过融合三种互补时间聚合方法的优点来自适应地聚合时间信息。大量实验证明了所提出的 MetaGait 的最先进性能。在 CASIA-B 上，我们在三种条件下分别取得 98.7%、96.0% 和 89.3% 的 rank-1 准确率。在 OU-MVLP 上，我们取得 92.4% 的 rank-1 准确率。
英文摘要：
Gait recognition, which aims at identifying individuals by their walking patterns, has recently drawn increasing research attention. However, gait recognition still suffers from the conflicts between the limited binary visual clues of the silhouette and numerous covariates with diverse scales, which brings challenges to the model's adaptiveness. In this paper, we address this conflict by developing a novel MetaGait that learns to learn an omni sample adaptive representation. Towards this goal, MetaGait injects meta-knowledge, which could guide the model to perceive sample-specific properties, into the calibration network of the attention mechanism to improve the adaptiveness from the omni-scale, omni-dimension, and omni-process perspectives. Specifically, we leverage the meta-knowledge across the entire process, where Meta Triple Attention and Meta Temporal Pooling are presented respectively to adaptively capture omni-scale dependency from spatial/channel/temporal dimensions simultaneously and to adaptively aggregate temporal information through integrating the merits of three complementary temporal aggregation methods. Extensive experiments demonstrate the state-of-the-art performance of the proposed MetaGait. On CASIA-B, we achieve rank-1 accuracy of 98.7%, 96.0%, and 89.3% under three conditions, respectively. On OU-MVLP, we achieve rank-1 accuracy of 92.4%.
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。
