The application is detecting the presence of a netted bag in an image. The image can contain fruit and vegetables, either with or without a netted bag around them, or below them (no constraints about placement of the netted bag). The question is: would you rather use a detector algorithm (YoloVx) or rather a classification model: 2 classes - netted fruit vs not-netted fruit. I'm leaning towards the first, but would like your input.
The images are very similar to the one below: