Search Results for author: Yingjing Lu

Found 3 papers, 1 papers with code

Not All Features Are Equal: Feature Leveling Deep Neural Networks for Better Interpretation

1 code implementation ICLR 2020 Yingjing Lu, Runde Yang

Self-explaining models are models that reveal decision making parameters in an interpretable manner so that the model reasoning process can be directly understood by human beings.

Decision Making

The Level Weighted Structural Similarity Loss: A Step Away from the MSE

no code implementations30 Apr 2019 Yingjing Lu

The Mean Square Error (MSE) has shown its strength when applied in deep generative models such as Auto-Encoders to model reconstruction loss.


Cross Domain Image Generation through Latent Space Exploration with Adversarial Loss

no code implementations24 May 2018 Yingjing Lu

Conditional domain generation is a good way to interactively control sample generation process of deep generative models.

Image Generation

Cannot find the paper you are looking for? You can Submit a new open access paper.