DeepAI AI Chat
Log In Sign Up

Mask Point R-CNN

by   Wenchao Zhang, et al.

The attributes of object contours has great significance for instance segmentation task. However, most of the current popular deep neural networks do not pay much attention to the target edge information. Inspired by the human annotation process when making instance segmentation datasets, in this paper, we propose Mask Point RCNN aiming at promoting the neural networks attention to the target edge information, which can heighten the information propagates between multiple tasks by using different attributes features. Specifically, we present an auxiliary task to Mask RCNN, including utilizing keypoint detection technology to construct the target edge contour, and enhancing the sensitivity of the network to the object edge through multi task learning and feature fusion. These improvements are easy to implement and have a small amount of additional computing overhead. By extensive evaluations on the Cityscapes dataset, the results show that our approach outperforms vanilla Mask RCNN by 5.4 on the validation subset and 5.0 on the test subset.


page 3

page 4

page 6


Faster Training of Mask R-CNN by Focusing on Instance Boundaries

We present an auxiliary task to Mask R-CNN, an instance segmentation net...

Mask R-CNN

We present a conceptually simple, flexible, and general framework for ob...

Path Aggregation Network for Instance Segmentation

The way that information propagates in neural networks is of great impor...

supervised adptive threshold network for instance segmentation

Currently, instance segmentation is attracting more and more attention i...

HAISTA-NET: Human Assisted Instance Segmentation Through Attention

Instance segmentation is a form of image detection which has a range of ...

PMODE: Prototypical Mask based Object Dimension Estimation

Can a neural network estimate an object's dimension in the wild? In this...

Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network

With more and more household objects built on planned obsolescence and c...