2 papers
cs.CV2024
The Last Mile to Supervised Performance: Semi-Supervised Domain Adaptation for Semantic Segmentation
Daniel Morales-Brotons, Grigorios Chrysos, Stratis Tzoumas +1
Supervised deep learning requires massive labeled datasets, but obtaining annotations is not always easy or possible, especially for dense tasks like semantic segmentation. To over…
cs.LG2024
Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits
Daniel Morales-Brotons, Thijs Vogels, Hadrien Hendrikx
Weight averaging of Stochastic Gradient Descent (SGD) iterates is a popular method for training deep learning models. While it is often used as part of complex training pipelines t…