AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Is Classification More Complex Than Vision to Ask?
The most complex task, I would say maybe is object detection because it involves sort of maybe predicting intermediate boxes. But even that is cast as a classification problem. And what about things like VQA visual question answering? Do you think of that more of an NLP task than a vision to ask or? It's again unclear. We really can't tell how effective these methods are because we don't have a good sense of these tasks.