Object category learning and retrieval with weak supervision

arXiv: Computer Vision and Pattern Recognition, Volume abs/1801.08985, 2017.

Cited by: 7|Bibtex|Views40|Links
EI

Abstract:

We consider the problem of retrieving objects from image data and learning to classify them into meaningful semantic categories with minimal supervision. To that end, we propose a fully differentiable unsupervised deep clustering approach to learn semantic classes in an end-to-end fashion without individual class labeling using only unlab...More

Code:

Data:

Your rating :
0

 

Tags
Comments