Statistically Consistent Saliency Estimation

Luo, Shunyan; Barut, Emre

doi:10.1109/iccv48922.2021.00078

Cited by 2 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specificity and relevance are introduced as two criteria for more accurate saliency maps (Gupta et al, 2020). In this work, we integrate a saliency method, LEG (Luo et al, 2021), into our framework as an offline explanation tool for certification agencies.…”

Section: Related Workmentioning

confidence: 99%

“…Linearly Estimated Gradient (LEG) (Luo et al, 2021) is a saliency method that recovers the gradient of a neural network by perturbing its input features. Features that contribute more to the network output will have gradients with larger magnitudes.…”

Section: Linearly Estimated Gradientmentioning

confidence: 99%

“…The distribution F is chosen based on the range of points to be considered. It can be proved that LEG has an analytical solution under certain conditions [Lemma 1 in Luo et al (2021)]. Specifically, let Z be a vector of random variables which obeys a centered distribution F, i.e., Z ~F and E[Z] 0.…”

Section: Linearly Estimated Gradientmentioning

confidence: 99%

“…We propose a novel framework that integrates an SDT and a saliency method called linearly estimated gradient (LEG) (Luo et al, 2021), to provide stepwise explanations for human users, as shown in Figure 1. The SDT serves as an online explanation provider to display critical information for human operators in real-time, while LEG is an offline explanation tool for certification agencies to conduct more comprehensive analyses.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Exploring online and offline explainability in deep reinforcement learning for aircraft separation assurance

Guo¹,

Zhou²,

Wei³

2022

Front. Aerosp. Eng.

View full text Add to dashboard Cite

Deep Reinforcement Learning (DRL) has demonstrated promising performance in maintaining safe separation among aircraft. In this work, we focus on a specific engineering application of aircraft separation assurance in structured airspace with high-density air traffic. In spite of the scalable performance, the non-transparent decision-making processes of DRL hinders human users from building trust in such learning-based decision making tool. In order to build a trustworthy DRL-based aircraft separation assurance system, we propose a novel framework to provide stepwise explanations of DRL policies for human users. Based on the different needs of human users, our framework integrates 1) a Soft Decision Tree (SDT) as an online explanation provider to display critical information for human operators in real-time; and 2) a saliency method, Linearly Estimated Gradient (LEG), as an offline explanation tool for certification agencies to conduct more comprehensive verification time or post-event analyses. Corresponding visualization methods are proposed to illustrate the information in the SDT and LEG efficiently: 1) Online explanations are visualized with tree plots and trajectory plots; 2) Offline explanations are visualized with saliency maps and position maps. In the BlueSky air traffic simulator, we evaluate the effectiveness of our framework on case studies with complex airspace route structures. Results show that the proposed framework can provide reasonable explanations of multi-agent sequential decision-making. In addition, for more predictable and trustworthy DRL models, we investigate two specific patterns that DRL policies follow based on similar aircraft locations in the airspace.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Linearly Estimated Gradientmentioning

confidence: 99%

Section: Linearly Estimated Gradientmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations