Robust Uncertainty Estimation for Classification of Maritime Objects
This work addresses uncertainty estimation for maritime object classification, which is an incremental advancement in a domain-specific application.
The paper tackles the problem of robust uncertainty estimation for classifying maritime objects by combining Monte Carlo Dropout with outlier detection techniques, resulting in improvements such as an 8% reduction in FPR95 compared to the highest-performing work and a 44.2% improvement over a baseline on the SHIPS dataset.
We explore the use of uncertainty estimation in the maritime domain, showing the efficacy on toy datasets (CIFAR10) and proving it on an in-house dataset, SHIPS. We present a method joining the intra-class uncertainty achieved using Monte Carlo Dropout, with recent discoveries in the field of outlier detection, to gain more holistic uncertainty measures. We explore the relationship between the introduced uncertainty measures and examine how well they work on CIFAR10 and in a real-life setting. Our work improves the FPR95 by 8% compared to the current highest-performing work when the models are trained without out-of-distribution data. We increase the performance by 77% compared to a vanilla implementation of the Wide ResNet. We release the SHIPS dataset and show the effectiveness of our method by improving the FPR95 by 44.2% with respect to the baseline. Our approach is model agnostic, easy to implement, and often does not require model retraining.