Search Results for author:
Found 4 papers, 1 papers with code
Preprint: Norm Loss: An efficient yet effective regularization method for deep neural networks
In this work we propose a weight soft-regularization method based on the Oblique manifold.
PREPRINT: Comparison of deep learning and hand crafted features for mining simulation data
The output of such simulations, in particular the calculated flow fields, are usually very complex and hard to interpret for realistic three-dimensional real-world applications, especially if time-dependent simulations are investigated.
On the Exploration of Incremental Learning for Fine-grained Image Retrieval
On the other hand, fine-tuning the learned representation only with the new classes leads to catastrophic forgetting.
A Comparison of CNN and Classic Features for Image Retrieval
Many methods use image gradients in different stages of the detection-description pipeline to describe local image structures.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
