GAN Mask R-CNN:Instance semantic segmentation benefits from generativeadversarial networks

10/26/2020
by   Quang H. Le, et al.
0

In designing instance segmentation ConvNets that reconstruct masks, segmentation is often taken as its literal definition – assigning label to every pixel – for defining the loss functions. That is, using losses that compute the difference between pixels in the predicted (reconstructed) mask and the ground truth mask – a template matching mechanism. However, any such instance segmentation ConvNet is a generator, so we can lay the problem of predicting masks as a GANs game framework: We can think the ground truth mask is drawn from the true distribution, and a ConvNet like Mask R-CNN is an implicit model that infers the true distribution. Then, designing a discriminator in front of this generator will close the loop of GANs concept and more importantly obtains a loss that is trained not hand-designed. We show this design outperforms the baseline when trying on, without extra settings, several different domains: cellphone recycling, autonomous driving, large-scale object detection, and medical glands. Further, we observe in general GANs yield masks that account for better boundaries, clutter, and small details.

READ FULL TEXT

page 1

page 6

page 7

page 8

page 9

page 12

research
02/22/2021

Contour Loss for Instance Segmentation via k-step Distance Transformation Image

Instance segmentation aims to locate targets in the image and segment ea...
research
05/04/2023

HAISTA-NET: Human Assisted Instance Segmentation Through Attention

Instance segmentation is a form of image detection which has a range of ...
research
12/03/2020

BoxInst: High-Performance Instance Segmentation with Box Annotations

We present a high-performance method that can achieve mask-level instanc...
research
07/17/2020

Boundary-preserving Mask R-CNN

Tremendous efforts have been made to improve mask localization accuracy ...
research
07/30/2020

LevelSet R-CNN: A Deep Variational Method for Instance Segmentation

Obtaining precise instance segmentation masks is of high importance in m...
research
04/20/2020

Utilizing Mask R-CNN for Waterline Detection in Canoe Sprint Video Analysis

Determining a waterline in images recorded in canoe sprint training is a...
research
11/12/2018

Learning Segmentation Masks with the Independence Prior

An instance with a bad mask might make a composite image that uses it lo...

Please sign up or login with your details

Forgot password? Click here to reset