4
$\begingroup$

Suppose a CNN is trained to detect bounding box of a certain type of object (people, cars, houses, etc.)

If each image in the training set contains just one object (and its corresponding bounding box), how well can a CNN generalize to pick up all objects if the input for prediction contains multiple objects?

Should the training images be downsampled in order for the CNN to pick out multiple objects in the prediction?

I don't have a specific one in mind. I was just curious about the general behavior.

$\endgroup$
  • $\begingroup$ "How well" means there should be a measure. Please include this in your question. Otherwise one could simply answer "really well" or "42%" $\endgroup$ – Martin Thoma Sep 27 '18 at 5:57
1
$\begingroup$

I suggest you to go through the r-cnn paper or go through a tutorial on it . CNNs transform the image into high dimensional vector in their last layer , in case of classification this vector is sent to a "softmax" layer , in case of bounding box regression , four values :length , breadth , location of one of the points of the bounding box , are regressed from this vector , so if you use a cnn with one regression head you end up with one bounding box irrespective of the training set.

| improve this answer | |
$\endgroup$
0
$\begingroup$

Typically, there are mainly three steps in an object bounding box detection.

First, a model or algo is used to generate ROI(region of interest) or region proposals. These region proposals are an all large set of bounding boxes spanning the full images. (that is, an object localization component).

In the second step, visual features(Face, Person, etc... using Convolution) are extracted for each of the bounding boxes, they are evaluated. It is determined whether and which objects are present in the interested area based on visual features (i.e. an object classification component).

In the final post-processing step, overlapped boxes are combined into a single bounding box (that is, non-maximum suppression).

| improve this answer | |
$\endgroup$

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.