Authors - Michele Della Ventura Abstract - Feature representations that are both high-dimensional and reduce redundancy often prove to be significant constraints on the performance of object detection. In this study, we present the first hybrid metaheuristic feature selection framework that combines the enhanced grey wolf optimizer (EGWO) and firefly algorithm (FA) with a deep learning-based detection pipeline. The proposed EGWO-EFA method for identifying useful and compact feature subsets has been shown to reduce dimensionality by over 99.99% on the Pascal VOC and Brain Tumor M2PBP datasets. The experiments conducted demonstrate that, compared to classical feature selection, this method has an improved F1-score and precision, by an average of 2%. In addition, the overall pipeline execution time is considerably shorter. These results show that hybrid metaheuristic optimization is an effective approach to scalable and efficient object detection for high-dimensional feature representations.
Open Zoom