Object category learning and retrieval with weak supervision
arXiv: Computer Vision and Pattern Recognition, Volume abs/1801.08985, 2017.
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
Full Text (Upload PDF)
PPT (Upload PPT)