# Layered Embeddings for Amodal Instance Segmentation

Source: [Layered Embeddings for Amodal Instance Segmentation](<https://www.sota2.com/research/paper/68fa67051e209131cea13d13>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:04:19.938Z

Authors: Yanfeng Liu, Eric Psota, Lance P\\'erez

Published: 2020-02-14T22:00:45.000Z

## Abstract

The proposed method extends upon the representational output of semantic instance segmentation by explicitly including both visible and occluded parts. A fully convolutional network is trained to produce consistent pixel-level embedding across two layers such that, when clustered, the results convey the full spatial extent and depth ordering of each instance. Results demonstrate that the network can accurately estimate complete masks in the presence of occlusion and outperform leading top-down bounding-box approaches. Source code available at https://github.com/yanfengliu/layered\_embeddings

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2002.06264>)

[PDF](<https://arxiv.org/pdf/2002.06264.pdf>)
