arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.01266cs.CVcs.AIcs.LG
收藏

可解释的深度跟踪

Interpretable Deep Tracking

University of Waterloo(滑铁卢大学)

Benjamin Thérien, Krzysztof Czarnecki

摘要:

想象一下,作为一辆自动驾驶汽车的乘客,你会经历一场车祸。你不想知道为什么会这样吗?目前用于3D检测、多目标跟踪和运动预测的端到端可优化深度神经网络(DNN)几乎没有解释它们是如何做出决策的。为了帮助弥合这一差距,我们设计了一个端到端的可优化的多目标跟踪架构和训练协议的启发,最近提出的方法的交换干预训练(IIT)。通过列举不同的跟踪决策和相关的推理过程,我们可以训练单个网络通过IIT来推理可能的决策。每个网络的决策都可以由它所训练的高级结构因果模型(SCM)来解释。此外,我们提出的模型学习对这些结果进行排名,在端到端训练中利用深度学习的承诺,同时具有内在的可解释性。

英文摘要:

Imagine experiencing a crash as the passenger of an autonomous vehicle. Wouldn't you want to know why it happened? Current end-to-end optimizable deep neural networks (DNNs) in 3D detection, multi-object tracking, and motion forecasting provide little to no explanations about how they make their decisions. To help bridge this gap, we design an end-to-end optimizable multi-object tracking architecture and training protocol inspired by the recently proposed method of interchange intervention training (IIT). By enumerating different tracking decisions and associated reasoning procedures, we can train individual networks to reason about the possible decisions via IIT. Each network's decisions can be explained by the high-level structural causal model (SCM) it is trained in alignment with. Moreover, our proposed model learns to rank these outcomes, leveraging the promise of deep learning in end-to-end training, while being inherently interpretable.

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。

↑