Given an image with multiple objects within it, I would like to train a CNN to output vector of labels corresponding to the presence/absence of objects within the image. I would like to know whether there are publications/experimental work on such an approach to gauge it's feasibility on whether it is possible to implement it for my own use case. So far, I haven't been able to find literature on multi-object detection within a single class.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.