5
$\begingroup$

I'm fairly new at computer vision and I've read an explanation at a medium post, however it still isn't clear for me how they truly differ.

$\endgroup$
5
$\begingroup$
  • Object Detection : is the technology that is related to computer vision and image processing. It's aim? detect objects in an image.
  • Semantic Segmentation : is a technique that detects , for each pixel , the object category it belongs to , all object categories ( labels ) must be known to the model.
  • Instance Segmentation : same as Semantic Segmentation, but dives a bit deeper, it identifies , for each pixel, the object instance it belongs to.

Here's an example of the main difference.

Differences

In the second image where Semantic Segmentation is applied, the category ( chair ) is one of the outputs, all chairs are colored the same. In the third image, the Instance Segmentation, goes a step further and separates the instances ( the chairs ) from one another apart from identifying the category ( chair ) in the first step.

Hope this clears it up for you a bit.

|improve this answer|||||
$\endgroup$
  • $\begingroup$ Thank you for your answer! You've clarified it for me! To make sure I understand, could I say that both type of segmentations are object detection techniques and that instance is a "higher form" of segmentation, since it does not only segment an object from others categories, but also between each instance of its own category? $\endgroup$ – Guilherme Marques May 15 '19 at 17:53
  • $\begingroup$ Exactly, thats it! $\endgroup$ – Blenz May 16 '19 at 8:21

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.