Sangdaow Noppitak

แสงดาว นพพิทักษ์

Profile: Scopus, research gate, google scholar

Thesis

Publications

We proposed a drop cyclic cosine learning rate schedule, called dropCyclic. The dropCyclic is the systematic reduction of the learning rate during training. This research aims to decrease the learning rate that cuts by a constant factor called the drop parameter, every constant number of epochs.The dropCyclic is also efficient in discovering the diversity of local minimums.
Ensemble CNNs
  • S. Noppitak, S. Gonwirat, and O. Surinta (2020). Instance Segmentation of Water Body from Aerial Image using Mask Region-based Convolutional Neural Network, in Information Science and System (ICISS), The 3rd International Conference on, 61-66. slidevideohttps://doi.org/10.1145/3388176.3388184
Mask R-CNN Framework