Motivated by this, we first design a process to stimulate peaks to emerge from a class response map.
#12 best model for Semantic Segmentation on PASCAL VOC 2012 val
For generating the pseudo labels, we first identify confident seed areas of object classes from attention maps of an image classification model, and propagate them to discover the entire instance areas with accurate boundaries.
We present a weakly supervised model that jointly performs both semantic- and instance-segmentation -- a particularly relevant problem given the substantial cost of obtaining pixel-perfect annotation for these tasks.
#15 best model for Panoptic Segmentation on Cityscapes val
This paper presents a weakly supervised instance segmentation method that consumes training data with tight bounding box annotations.