MelNet: A Real-Time Deep Learning Algorithm for Object Detection
This is an incremental improvement for object detection in autonomous driving scenarios using the KITTI dataset.
The authors introduced MelNet, a deep learning algorithm for object detection, and trained it on the KITTI dataset, achieving an mAP score of 0.732 after 300 epochs. They found that training a new model like MelNet on a specific dataset can outperform some pre-trained models like EfficientDet after 150 epochs.
In this study, a novel deep learning algorithm for object detection, named MelNet, was introduced. MelNet underwent training utilizing the KITTI dataset for object detection. Following 300 training epochs, MelNet attained an mAP (mean average precision) score of 0.732. Additionally, three alternative models -YOLOv5, EfficientDet, and Faster-RCNN-MobileNetv3- were trained on the KITTI dataset and juxtaposed with MelNet for object detection. The outcomes underscore the efficacy of employing transfer learning in certain instances. Notably, preexisting models trained on prominent datasets (e.g., ImageNet, COCO, and Pascal VOC) yield superior results. Another finding underscores the viability of creating a new model tailored to a specific scenario and training it on a specific dataset. This investigation demonstrates that training MelNet exclusively on the KITTI dataset also surpasses EfficientDet after 150 epochs. Consequently, post-training, MelNet's performance closely aligns with that of other pre-trained models.