Abstract
This paper presents deterioration level estimation based on convolutional neural networks using a confidence-aware attention mechanism for infrastructure inspection. Spatial attention mechanisms try to highlight the important regions in feature maps for estimation by using an attention map. The attention mechanism using an effective attention map can improve feature maps. However, the conventional attention mechanisms have a problem as they fail to highlight important regions for estimation when an ineffective attention map is mistakenly used. To solve the above problem, this paper introduces the confidence-aware attention mechanism that reduces the effect of ineffective attention maps by considering the confidence corresponding to the attention map. The confidence is calculated from the entropy of the estimated class probabilities when generating the attention map. Because the proposed method can effectively utilize the attention map by considering the confidence, it can focus more on the important regions in the final estimation. This is the most significant contribution of this paper. The experimental results using images from actual infrastructure inspections confirm the performance improvement of the proposed method in estimating the deterioration level.
Highlights
Accepted: 2 January 2022The number of aging infrastructures is increasing around the world [1,2], and techniques to support engineers in maintaining infrastructures efficiently are required
Deterioration level estimation based on confidence-aware attention branch network (ABN) (ConfABN), which can control the influence of an attention map on feature maps according to the confidence, is proposed for infrastructure inspection
The confidence-aware attention mechanism can reduce the negative effects of ineffective attention maps that are likely to be generated in the early training process
Summary
The number of aging infrastructures is increasing around the world [1,2], and techniques to support engineers in maintaining infrastructures efficiently are required. An attention branch network (ABN), which uses an attention map generated during the CNN-based estimation to improve estimation performance and explain the estimation results, has been proposed [10]. The performance of the deterioration level estimation improves significantly by controlling the influence of the attention map on the feature maps according to the above confidence. Deterioration level estimation based on confidence-aware ABN (ConfABN), which can control the influence of an attention map on feature maps according to the confidence, is proposed for infrastructure inspection. Since ConfABN can provide confidence in the attention map of the estimation results, it achieves higher explainability for the output than previous attention-based methods, such as ABN [10].
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have