Home /
Research
Showing 337 - 342 / 897
Characterization of Industrial Smoke Plumes from Remote Sensing Data
MichaelMommert, MarioSigel, MarcelNeuhausler....
Published date-11/23/2020
The major driver of global warming has been identified as the anthropogenic release of greenhouse gas (GHG) emissions from industrial activities. The quantitative monitoring of these emissions is mandatory to …
Stable Weight Decay Regularization
ZekeXie, IsseiSato, MasashiSugiyama....
Published date-11/23/2020
Weight decay is a popular regularization technique for training of deep neural networks. Modern deep learning libraries mainly use $L_{2}$ regularization as the default implementation of weight decay. \citet{loshchilov2018decoupled} demonstrated …
Peeking inside the Black Box: Interpreting Deep Learning Models for Exoplanet Atmospheric Retrievals
KaiHouYip, QuentinChangeat, NikolaosNikolaou....
Published date-11/23/2020
Deep learning algorithms are growing in popularity in the field of exoplanetary science due to their ability to model highly non-linear relations and solve interesting problems in a data-driven manner. …
Learnable Boundary Guided Adversarial Training
JiequanCui, ShuLiu, LiWeiWang....
Published date-11/23/2020
AdversarialDefense
Previous adversarial training raises model robustness under the compromise of accuracy on natural data. In this paper, our target is to reduce natural accuracy degradation. We use the model logits …
Detection of Double-Nuclei Galaxies in SDSS
Bhattacharya, Anwesh, Saha....
Published date-11/23/2020
It is now well established that galaxy interactions and mergers play a crucial role in the hierarchical growth of structure in our universe. Galaxy mergers can lead to the formation …
SCGAN: Saliency Map-guided Colorization with Generative Adversarial Network
YuzhiZhao, Lai-ManPo, Kwok-WaiCheung....
Published date-11/23/2020
Colorization
Given a grayscale photograph, the colorization system estimates a visually plausible colorful image. Conventional methods often use semantics to colorize grayscale images. However, in these methods, only classification semantic information …