DeepAI AI Chat
Log In Sign Up

Bounding Box Embedding for Single Shot Person Instance Segmentation

by   Jacob Richeimer, et al.

We present a bottom-up approach for the task of object instance segmentation using a single-shot model. The proposed model employs a fully convolutional network which is trained to predict class-wise segmentation masks as well as the bounding boxes of the object instances to which each pixel belongs. This allows us to group object pixels into individual instances. Our network architecture is based on the DeepLabv3+ model, and requires only minimal extra computation to achieve pixel-wise instance assignments. We apply our method to the task of person instance segmentation, a common task relevant to many applications. We train our model with COCO data and report competitive results for the person class in the COCO instance segmentation task.


page 1

page 2

page 3

page 4


Pixel Consensus Voting for Panoptic Segmentation

The core of our approach, Pixel Consensus Voting, is a framework for ins...

Incremental Few-Shot Instance Segmentation

Few-shot instance segmentation methods are promising when labeled traini...

Accelerating the creation of instance segmentation training sets through bounding box annotation

Collecting image annotations remains a significant burden when deploying...

Towards Bounding-Box Free Panoptic Segmentation

In this work we introduce a new bounding-box free network (BBFNet) for p...

Pose2Instance: Harnessing Keypoints for Person Instance Segmentation

Human keypoints are a well-studied representation of people.We explore h...

Instance Segmentation of Biomedical Images with an Object-aware Embedding Learned with Local Constraints

Automatic instance segmentation is a problem that occurs in many biomedi...