crowdAI is shutting down - please read our blog post for more information
Building Missing Maps with Machine Learning
By Humanity & Inclusion
about 2 years ago
It seems that the models trained on competition dataset alone (as required) may not generalize to well due to the homogenous nature of the dataset.
We are thinking about retraining (or finetuning) the model with heavy augmentations and use scale/color TTA at inference.
What are your ideas?