Search Results for author:
Found 4 papers, 1 papers with code
Bag of Negatives for Siamese Architectures
Training a Siamese architecture for re-identification with a large number of identities is a challenging task due to the difficulty of finding relevant negative samples efficiently.
Unsupervised Deep Feature Extraction for Remote Sensing Image Classification
This paper introduces the use of single layer and deep convolutional networks for remote sensing data analysis.
FitNets: Hints for Thin Deep Nets
In this paper, we extend this idea to allow the training of a student that is deeper and thinner than the teacher, using not only the outputs but also the intermediate representations learned by the teacher as hints to improve the training process and final performance of the student.
No more meta-parameter tuning in unsupervised sparse feature learning
We propose a meta-parameter free, off-the-shelf, simple and fast unsupervised feature learning algorithm, which exploits a new way of optimizing for sparsity.
Ranked #104 on
Image Classification
on STL-10
