# Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation

## TL;DR

This paper introduces a semantics-aware distance map representation and a semantic layering network architecture for amodal instance segmentation, achieving state-of-the-art results on COCOA and D2SA datasets.

## Contribution

The work proposes a novel sem-dist map representation and a CNN architecture for layered amodal segmentation, depth, and occlusion estimation.

## Key findings

- Achieves state-of-the-art performance on COCOA and D2SA datasets.
- Effectively predicts amodal segmentation, occlusion, and depth order.
- Introduces a new level-set based representation for segmentation tasks.

## Abstract

In this work, we demonstrate yet another approach to tackle the amodal segmentation problem. 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. The sem-dist map is a kind of level-set representation, of which the different regions of an object are placed into different levels on the map according to their visibility. It is a natural extension of masks and heatmaps, where modal, amodal segmentation, as well as depth order information, are all well-described. Then we also introduce a novel convolutional neural network (CNN) architecture, which we refer to as semantic layering network, to estimate sem-dist maps layer by layer, from the global-level to the instance-level, for all objects in an image. Extensive experiments on the COCOA and D2SA datasets have demonstrated that our framework can predict amodal segmentation, occlusion and depth order with state-of-the-art performance.