Simple Does It: Weakly Supervised Instance and Semantic Segmentation

Anna Khoreva, Rodrigo Benenson, Jan Hosang, Matthias Hein, Bernt Schiele; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 876-885

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.