NoPeopleAllowed: The Three-Step Approach to Weakly Supervised Semantic Segmentation
This addresses the problem of reducing annotation costs for semantic segmentation in computer vision, though it is incremental.
The paper tackles weakly supervised semantic segmentation using only image-level annotations, achieving 37.34 mean IoU on the test set and placing 3rd at the LID Challenge.
We propose a novel approach to weakly supervised semantic segmentation, which consists of three consecutive steps. The first two steps extract high-quality pseudo masks from image-level annotated data, which are then used to train a segmentation model on the third step. The presented approach also addresses two problems in the data: class imbalance and missing labels. Using only image-level annotations as supervision, our method is capable of segmenting various classes and complex objects. It achieves 37.34 mean IoU on the test set, placing 3rd at the LID Challenge in the task of weakly supervised semantic segmentation.