Suppose that we have a labeled training set of $n$ closely cropped images of cars $(x_1, y_1) , \dots, (x_n, y_n)$. We then train a CNN on this. Let's say we have $m$ test images. Then for each of the $m$ images, do we use the trained CNN on a cropped out portion of the box to detect whether there is a car or not? If the object is large, wouldn't having a large sliding window have better performance than a smaller sliding window?