Layered Embeddings for Amodal Instance Segmentation

02/14/2020
by   Yanfeng Liu, et al.
0

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

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 4

page 7

03/12/2020

Conditional Convolutions for Instance Segmentation

We propose a simple yet effective instance segmentation framework, terme...
09/17/2019

AdaptIS: Adaptive Instance Selection Network

We present Adaptive Instance Selection network architecture for class-ag...
06/03/2018

TernausNetV2: Fully Convolutional Network for Instance Segmentation

The most common approaches to instance segmentation are complex and use ...
03/23/2021

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers

Segmenting highly-overlapping objects is challenging, because typically ...
04/10/2019

Instance Segmentation of Biological Images Using Harmonic Embeddings

We present a new instance segmentation approach tailored to biological i...
12/07/2021

Deep Level Set for Box-supervised Instance Segmentation in Aerial Images

Box-supervised instance segmentation has recently attracted lots of rese...
07/15/2021

Amodal segmentation just like doing a jigsaw

Amodal segmentation is a new direction of instance segmentation while co...

Code Repositories

layered_embeddings

Source code for paper "Layered Embeddings for Amodal Instance Segmentation"


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.