Segmenting highly-overlapping objects is challenging, because typically no distinction is made between real object contours and occlusion boundaries.
Ranked #1 on Instance Segmentation on KINS
We propose the network structure to reason invisible parts via a new multi-task framework with Multi-View Coding (MVC), which combines information in various recognition levels.
Specifically, we first introduce a new representation, namely a semantics-aware distance map (sem-dist map), to serve as our target for amodal segmentation instead of the commonly used masks and heatmaps.
Semantic amodal segmentation is a recently proposed extension to instance-aware segmentation that includes the prediction of the invisible region of each object instance.