用证据深度学习提升行人属性识别的可靠性。
Uncertainty-Aware Pedestrian Attribute Recognition via Evidential Deep Learning
- 引入证据深度学习，捕捉局部特征并估计不确定性。
- 在多个数据集上性能优于或相当现有方法。
- 适合需要可靠判断的复杂场景应用。
我们提出UAPAR，一种基于证据深度学习（EDL）的不确定性感知行人属性识别框架。这是首个将EDL应用于行人属性识别的研究。与传统确定性方法不同，该框架能有效识别低质量样本上的不可靠预测，增强复杂现实场景下的系统鲁棒性。UAPAR在基于CLIP的架构中引入区域感知证据推理模块，利用交叉注意力和空间先验掩码捕捉细粒度局部特征，并通过证据头估计属性级别的认知不确定性。为提升训练鲁棒性，设计了不确定性引导的双阶段课程学习策略，缓解严重标签噪声的影响。在PA100K、PETA、RAPv1和RAPv2数据集上的大量实验表明，UAPAR表现优异。定性结果验证了其生成的不确定性估计能有效预测困难或错误样本。
原文摘要 · Abstract (English)
We propose UAPAR, an Uncertainty-Aware Pedestrian Attribute Recognition framework. To the best of our knowledge, this is the first EDL-based uncertainty-aware framework for pedestrian attribute recognition (PAR). Unlike conventional deterministic methods, which fail to assess prediction reliability on low-quality samples, UAPAR effectively identifies unreliable predictions and thus enhances system robustness in complex real-world scenarios. To achieve this, UAPAR incorporates Evidential Deep Learning (EDL) into a CLIP-based architecture. Specifically, a Region-Aware Evidence Reasoning module employs cross-attention and spatial prior masks to capture fine-grained local features, which are further processed by an evidence head to estimate attribute-wise epistemic uncertainty. To further enhance training robustness, we develop an uncertainty-guided dual-stage curriculum learning strategy to alleviate the adverse effects of severe label noise during training. Extensive experiments on the PA100K, PETA, RAPv1, and RAPv2 datasets demonstrate that UAPAR achieves competitive or superior performance. Furthermore, qualitative results confirm that the proposed framework generates uncertainty estimates that are predictive of challenging or erroneous samples.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。