Simple Does It: Weakly Supervised Instance and Semantic Segmentation
This work addresses the annotation cost problem for computer vision researchers and practitioners, offering a significant improvement over previous weakly supervised methods.
The paper tackles the problem of costly annotations for semantic labeling and instance segmentation by proposing a weakly supervised approach using bounding box detection annotations, achieving ~95% of the quality of fully supervised models.
Semantic labelling and instance segmentation are two tasks that require particularly costly annotations. Starting from weak supervision in the form of bounding box detection annotations, we propose a new approach that does not require modification of the segmentation training procedure. We show that when carefully designing the input labels from given bounding boxes, even a single round of training is enough to improve over previously reported weakly supervised results. Overall, our weak supervision approach reaches ~95% of the quality of the fully supervised model, both for semantic labelling and instance segmentation.