通过自发现学习提升复杂驾驶行为识别准确率
Driving behavior recognition via self-discovery learning
- 设计自发现学习框架，自动挖掘样本内在语义特征
- 在真实驾驶数据集上达到92.3%识别准确率，优于基线方法3.6个百分点
- 特别适合处理样本稀少且易混淆的罕见驾驶行为识别场景
自动驾驶系统需要深入理解人类驾驶行为以实现更高智能与安全性。尽管深度学习取得进展，但样本稀缺导致的长尾分布及相似行为造成的混淆仍阻碍有效行为检测。现有方法难以充分解决样本混淆问题，因数据集中常存在模糊样本，遮蔽了独特语义信息。本文提出自发现学习框架，通过无监督机制挖掘样本间隐含差异，增强模型对细微行为差别的感知能力，在真实驾驶数据集上实现92.3%的识别准确率，显著优于现有方法。
原文摘要 · Abstract (English)
Autonomous driving systems require a deep understanding of human driving behaviors to achieve higher intelligence and safety.Despite advancements in deep learning, challenges such as long-tail distribution due to scarce samples and confusion from similar behaviors hinder effective driving behavior detection.Existing methods often fail to address sample confusion adequately, as datasets frequently contain ambiguous samples that obscure unique semantic information.
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。