Recently, many researchers have attempted to improve deep These detectors have achieved high accuracy rates but low operational learning-based object detection models, both in terms of accuracy speeds. To address this issue, single-stage detectors and operational speeds. However, frequently, there have been proposed. These detectors skip the region proposal is a tradeoff between speed and accuracy of such models, stage and make bounding box predictions directly from the which encumbers their use in practical applications such as input image. As a result, these models are faster but not as autonomous navigation. In this paper, we explore a metacognitive accurate as two-stage detectors. Among the single-stage detectors, learning strategy for object detection to improve Single Shot MultiBox Detector (SSD) [10], the You generalization ability while at the same time maintaining detection Only Look Once (YOLO) series of networks, and RetinaNet speed. The meta-cognitive method selectively samples [11] are the most representative. SSD directly produces class the object instances in the training dataset to reduce overfitting.