Open-Set Automatic Target Recognition

TL;DR

This paper introduces an open-set ATR framework with a plugin CBC module, enabling recognition of unknown classes during inference, and demonstrates superior performance over existing methods on benchmark datasets.

Contribution

It presents the first open-set ATR approach with a novel plugin CBC module that can be integrated into existing ATR algorithms for improved unknown class detection.

Findings

Outperforms existing open-set methods on DSIAC and CIFAR-10 datasets.

The CBC module can be trained end-to-end and integrated with any ATR algorithm.

First work addressing open-set classification in ATR applications.

Abstract

Automatic Target Recognition (ATR) is a category of computer vision algorithms which attempts to recognize targets on data obtained from different sensors. ATR algorithms are extensively used in real-world scenarios such as military and surveillance applications. Existing ATR algorithms are developed for traditional closed-set methods where training and testing have the same class distribution. Thus, these algorithms have not been robust to unknown classes not seen during the training phase, limiting their utility in real-world applications. To this end, we propose an Open-set Automatic Target Recognition framework where we enable open-set recognition capability for ATR algorithms. In addition, we introduce a plugin Category-aware Binary Classifier (CBC) module to effectively tackle unknown classes seen during inference. The proposed CBC module can be easily integrated with any existing ATR algorithms and can be trained in an end-to-end manner. Experimental results show that the proposed approach outperforms many open-set methods on the DSIAC and CIFAR-10 datasets. To the best of our knowledge, this is the first work to address the open-set classification problem for ATR algorithms. Source code is available at: https://github.com/bardisafa/Open-set-ATR.