Hi, I would like to do some object detection where have two restrictions. First one is that at the moment dont have large number of images for training (at the moment are around 550 images). Second, most likely I will not be able to see the whole object , so will be available only some part of the object that try to detect. My question is it worsted to try Deep Convolutional Networks
via Bayesian Optimization and Structured Prediction for this kind of situation. And also where can find some instruction regarding the software and code that can be used? I have this paper as a reference
http://web.eecs.umich.edu/~honglak/cvpr15-cnn-detection.pdf
Thanks