I want to design a model that can detect the different feature in the images, let's consider we have ~100000 images of cows. when I give this images to the model it has to identify different parts of the cow like eyes, feet, udder etc. How can I do this, one way is to label the images and train the model but is there an automatic detection of features from the images.
closed as too broad by Stephen Rauch♦, Rejaul Karim, OmG, ignatius, Toros91 Dec 14 '18 at 2:57
Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. Avoid asking multiple distinct questions at once. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.
There is an article by M Noroozi named: "Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles"
They use a CNN that is trained to solve jigsaw puzzles of images, which allows it to learn image representations without any human annotations. This is pretty much what you are asking for (unsupervised learning of image features). It is not a hard paper to read and you should look it up.