Distribution Reliability Assessment-Based Incremental Learning for Automatic Target Recognition

To rapidly improve the automatic target recognition (ATR) system when new unknown samples are constantly captured, it is necessary to examine the existing training samples and recognition model so that the ATR system could autonomously assess new unknown samples with low predictive reliability during the recognition process and learn them preferentially. Incremental learning methods generally consider forming key exemplar set from the existing known samples, but rarely managing updates of unknown samples. In this article, an incremental samples' evaluation and management method from the perspective of distribution-reliability-assessment-based incremental learning frame (DRaIL) is proposed, which realizes the retention of existent reliable exemplars and the predictive-reliability-assessment-based updating of new unknown samples simultaneously. DRaIL preserves the prior distribution in the high-density and overlap regions first, and then the classification reliability and 'in-of-distribution' reliability of new unknown samples are evaluated based on the consistency between the new and preserved distributions. Updating the new samples with low reliability using new labels could rapidly improve the classification surface and add new classes. Experimental results for the practical incremental learning scenario demonstrate the validity of the proposed DRaIL on representative exemplar selection and reliability ranking performance.