Layered Embeddings for Amodal Instance Segmentation

  title={Layered Embeddings for Amodal Instance Segmentation},
  author={Yanfeng Liu and Eric Psota and Lance C. P{\'e}rez},
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… 



Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling

This work presents a method that leverages a fully convolutional network (FCN) to predict semantic labels, depth and an instance-based encoding using each pixel’s direction towards its corresponding instance center.

Fully Convolutional Instance-Aware Semantic Segmentation

The first fully convolutional end-to-end solution for instance-aware semantic segmentation task, which achieves state-of-the-art performance in both accuracy and efficiency, wins the COCO 2016 segmentation competition by a large margin.

Semantic Instance Segmentation via Deep Metric Learning

A new method for semantic instance segmentation is proposed, by first computing how likely two pixels are to belong to the same object, and then by grouping similar pixels together, based on a deep, fully convolutional embedding model.

Semantic Instance Segmentation for Autonomous Driving

This work proposes a discriminative loss function, operating at pixel level, that encourages a convolutional network to produce a representation of the image that can easily be clustered into instances with a simple post-processing step.

Amodal Instance Segmentation

A new method for amodal instance segmentation, which represents the first such method to the best of the knowledge, is proposed and demonstrated both qualitatively and quantitatively.

Fully convolutional networks for semantic segmentation

The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.

Semantic Instance Segmentation with a Discriminative Loss Function

This work proposes an approach of combining an off-the-shelf network with a principled loss function inspired by a metric learning objective that encourages a convolutional network to produce a representation of the image that can easily be clustered into instances with a simple post-processing step.

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

This work extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries and applies the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network.

Semantic Amodal Segmentation

A detailed image annotation that captures information beyond the visible pixels and requires complex reasoning about full scene structure is proposed, and it is shown that the proposed full scene annotation is surprisingly consistent between annotators, including for regions and edges.

Multi-instance object segmentation with occlusion handling

This work proposes to incorporate top-down category specific reasoning and shape prediction through exemplars into an intuitive energy minimization framework for multi-instance object segmentation to tackle occlusions.