用于无约束步态识别的蒸馏引导表示学习
Distillation-guided Representation Learning for Unconstrained Gait Recognition
AI总结：
提出GADER框架，通过双螺旋签名检测步态片段、编码视角信息并从RGB模型蒸馏表示，显著提升了无约束场景下步态识别的鲁棒性和准确率。
摘要：
步态识别有望基于行走模式而非外观信息来稳健地识别对象。尽管以往方法在精心整理的室内数据上表现良好，但它们在无约束场景下往往表现不佳，例如户外、远距离场景等。我们提出了一个名为GAit DEtection and Recognition（GADER）的框架，用于在具有挑战性的户外场景中进行人体认证。具体而言，GADER利用双螺旋签名来检测包含人体运动的片段，并通过一种新颖的步态识别方法构建判别性特征，该方法仅使用包含步态信息的帧。为进一步增强鲁棒性，GADER在其架构中编码了视角信息，并从辅助的RGB识别模型中蒸馏表示，这使得GADER能够在训练时从轮廓和RGB数据中学习。在测试时，GADER仅从轮廓模态进行推断。我们在多个最先进的步态基线上评估了我们的方法，并展示了在室内和室外数据集上的一致改进，特别是在无约束的远程步态数据上取得了25.2%的显著改进。
英文摘要：
Gait recognition holds the promise of robustly identifying subjects based on walking patterns instead of appearance information. While previous approaches have performed well for curated indoor data, they tend to underperform in unconstrained situations, e.g. in outdoor, long distance scenes, etc. We propose a framework, termed GAit DEtection and Recognition (GADER), for human authentication in challenging outdoor scenarios. Specifically, GADER leverages a Double Helical Signature to detect segments that contain human movement and builds discriminative features through a novel gait recognition method, where only frames containing gait information are used. To further enhance robustness, GADER encodes viewpoint information in its architecture, and distills representation from an auxiliary RGB recognition model, which enables GADER to learn from silhouette and RGB data at training time. At test time, GADER only infers from the silhouette modality. We evaluate our method on multiple State-of-The-Arts(SoTA) gait baselines and demonstrate consistent improvements on indoor and outdoor datasets, especially with a significant 25.2% improvement on unconstrained, remote gait data.
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。
