3 papers
cs.DC2022
Disentangling Domain and Content
Dan Andrei Iliescu, Aliaksei Mikhailiuk, Damon Wischik +1
Many real-world datasets can be divided into groups according to certain salient features (e.g. grouping images by subject, grouping text by font, etc.). Often, machine learning ta…
eess.IV2021
Training a Task-Specific Image Reconstruction Loss
Aamir Mustafa, Aliaksei Mikhailiuk, Dan Andrei Iliescu +2
The choice of a loss function is an important factor when training neural networks for image restoration problems, such as single image super resolution. The loss function should e…
stat.ML2019
To Ensemble or Not Ensemble: When does End-To-End Training Fail?
Andrew M. Webb, Charles Reynolds, Wenlin Chen +4
End-to-End training (E2E) is becoming more and more popular to train complex Deep Network architectures. An interesting question is whether this trend will continue-are there any c…