We propose an approach to estimate the number of samples required for a ...
Annotating bounding boxes for object detection is expensive, time-consum...
Most existing works on few-shot object detection (FSOD) focus on a setti...
Class-incremental learning (CIL) has been widely studied under the setti...
We consider the problem of omni-supervised object detection, which can u...
In the last decade convolutional neural networks have become gargantuan....
Deep neural networks often require copious amount of labeled-data to tra...