3D semantic scene labeling is a fundamental task for Autonomous Driving. Imbalanced distribution of classes in the dataset is one of the challenges that face 3D semantic scene labeling task. This leads to misclassifying for the non-dominant classes which suffer from two main problems: rare appearance in the dataset, and few sensor points reflected from one object of these classes. Weighted Self-Incremental Transfer Learning is proposed as a generalized methodology that solves the imbalanced training dataset problems, as it re-weights the components of the loss function computed from individual classes based on their frequencies in the training dataset, and applies Self-Incremental Transfer Learning by running the Neural Network model on non-dominant classes first, then dominant classes one-by-one are added.

[wpforms id=”13896″]