Search Results for author:
Found 3 papers, 2 papers with code
Faster ISNet for Background Bias Mitigation on Deep Neural Networks
Representing a potentially massive training speed improvement over ISNet, the proposed architectures introduce LRP optimization into a gamut of applications that the original model cannot feasibly handle.
Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization
Features in images' backgrounds can spuriously correlate with the images' classes, representing background bias.
Conceptron: a probabilistic deep one-class classification method
One-class learning through deep architectures is a particularly challenging task; in this scenario the crasis of kernel methods and deep networks can represent a viable strategy to empower already effective methods.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
