for herbarium and plant images, segmented leaves, barks, and flowers can be separated into views, which can then be fed into feature extraction layers such as shapes and vines, followed by typical neurla networks or graph networks, and multi-task prediction on family-genus-species
multi-task training here make sense because the predicted, family, genus species is hierarchical by nature.
https://en.wikipedia.org/wiki/Species
Q: ImageNet Classification is inherently multi-task, is it?
vision transformers with attention, image with 16x16 words
https://arxiv.org/abs/2010.11929
No comments:
Post a Comment