The “absent training on that specific task” matters a lot here, as does the precise limits of “specific”. There are commercially-available facial-identification (not just recognition) systems that are good enough for real-money payments, and they don’t train on the specific faces to be recognized. Likewise commercial movement-tracking systems that care about history and continuity, in addition to image similarity (so, for instance, twins don’t confuse them).
A flower-identification set of models would be easier than this, I expect.
The “absent training on that specific task” matters a lot here, as does the precise limits of “specific”. There are commercially-available facial-identification (not just recognition) systems that are good enough for real-money payments, and they don’t train on the specific faces to be recognized. Likewise commercial movement-tracking systems that care about history and continuity, in addition to image similarity (so, for instance, twins don’t confuse them).
A flower-identification set of models would be easier than this, I expect.