Note: This is a wiki, please edit it & add resources!
YouTube Link: PyTorch Book Reading - 8. U-net, Image Segmentation and Image Augmentations in PyTorch - YouTube
Hey again, everybody!
Last week we got a vanilla introduction to image augmentations, this week we’ll take an in depth look, and understand what is image segmentation and learn about the U-net Architecture!
Link to sign up
When would you rather use Segmentation over Classification?
I guess we use classification when we care about the presence/absence of an object in an image. And we use segmentation when we care about the exact position of an object in the image.
When we want to also know the location of objects (thanks for the feedback ) in the images.
Medical imaging/ classify the pixels
Basically, classify different objects in one image
Image Segmentation is primarily used when we want to understand the entire context of various contents in the image. The context here means: accurately identifying the position of different objects in an image.
- Image Masking(the one we use in zoom to add virtual background)
- Self-driving cars.
- Medical Imaging
When would you Segment a tumour? After classification or before?
After classification, because we want to see finer level details where the tumour is present.
My guess is that we should segment BEFORE classification so that we can only send the part of the image that may contain a tumor to our classification model to classify it as benign/malignant.
to train the model we need to segment it before
I am thinking, before classification. Maybe we can segment( not sure how? but…) and then easily crop and classify.
Based on the pipeline detailed in the book, segmentation is performed before classification to isolate nodules.
UNet has been out for a few years. Do you know of any significant improvements to UNet architecture for segmentation?
Up sampling is basically resizing . Right?
Homework convert this to Torch