Transfer Learning Method for Object Detection Model Using Genetic Algorithm

This paper proposes a transfer learning method for an object detection model using a genetic algorithm to solve the difficulty of the conventional transfer learn-ing of deep learning-based object detection models. The genetic algorithm of the proposed method can se-lect the re-learning layers automatically in the trans-fer learning process instead of a trial-and-error selec-tion of the conventional method. Transfer learning was performed using the EfficientDet-d0 model pre -trained on the COCO dataset and the Global Wheat Head Detection (GWHD) dataset, and experiments were conducted to compare fine-tuning and the pro-posed method. Using the training data and the vali-dation data of the GWHD, we compare the mean av-erage precision (mAP) of the models trained by the conventional and the proposed methods, respectively, on the test data of the GWHD. It is confirmed that the model trained by the proposed method has higher performance than the model trained by the conven-tional method. The average of mAP of the proposed method, which automatically selects the re-learning layer (approximate to 0.603), is higher than the average of mAP of the conventional method (approximate to 0.594). Furthermore, the standard deviation of results obtained by the pro-posed method is smaller than that of the conventional method, and it shows the stable learning process of the method.