Is there any deep learning object detection algorithms that can work without bounding boxes annotated data?


For example Haar Cascade can be trained using only positive and negative examples, you don't need any bounding box annotations. But it not a deep learning approach.

Another example can be the most straight forward Image recognition model + sliding window. But it is very slow

deep batch

Posted 2018-11-05T17:57:00.960

Reputation: 21

No answers