Filtering the labels of mobilenetV3

I have a project that i need to detect Persons, and i’m using the fasterrcnn_mobilenet_v3_large_fpn model to do that. But this model has several classes:

[
background’, ‘person’, ‘bicycle’, ‘car’, ‘motorcycle’, ‘airplane’, ‘bus’,
‘train’, ‘truck’, ‘boat’, ‘traffic light’, ‘fire hydrant’, ‘stop sign’,
‘parking meter’, ‘bench’, ‘bird’, ‘cat’, ‘dog’, ‘horse’, ‘sheep’, ‘cow’,
‘elephant’, ‘bear’, ‘zebra’, ‘giraffe’, ‘backpack’, ‘umbrella’, ‘handbag’,
‘tie’, ‘suitcase’, ‘frisbee’, ‘skis’, ‘snowboard’, ‘sports ball’, ‘kite’,
‘baseball bat’, ‘baseball glove’, ‘skateboard’, ‘surfboard’, ‘tennis racket’,
‘bottle’, ‘wine glass’, ‘cup’, ‘fork’, ‘knife’, ‘spoon’, ‘bowl’, ‘banana’,
‘apple’, ‘sandwich’, ‘orange’, ‘broccoli’, ‘carrot’, ‘hot dog’, ‘pizza’,
‘donut’, ‘cake’, ‘chair’, ‘couch’, ‘potted plant’, ‘bed’, ‘dining table’,
‘toilet’, ‘tv’, ‘laptop’, ‘mouse’, ‘remote’, ‘keyboard’, ‘cell phone’,
‘microwave’, ‘oven’, ‘toaster’, ‘sink’, ‘refrigerator’, ‘book’, ‘clock’,
‘vase’, ‘scissors’, ‘teddy bear’, ‘hair drier’, ‘toothbrush’
]

And i’m showing the detections only if the bounding box represents a Person, but I think that isn’t a smart thing to do, because in the end, all classes are being computed, only aren’t being showed. It is a good idea apply a Transfer Learning to only detect Persons? I saw several tutorials of people doing transfer learning on mobilenet, but their purpose is different: they want to add new classes to the model and remove others, I just want to continue detecting Persons and remove the other labels.