FourierNet: Compact mask representation for instance segmentation using differentiable shape decoders

02/07/2020
by   Nuri Benbarka, et al.
0

We present FourierNet a single shot, anchor-free, fully convolutional instance segmentation method, which predicts a shape vector that is converted into contour points using a numerical transformation. Compared to previous methods, we introduce a new training technique, where we utilize a differentiable shape decoder, which achieves automatic weight balancing of the shape vector's coefficients. Fourier series was utilized as a shape encoder because of its coefficient interpretability and fast implementation. By using its lower frequencies we were able to retrieve smooth and compact masks. FourierNet shows promising results compared to polygon representation methods, achieving 30.6 mAP on the MS COCO 2017 benchmark. At lower image resolutions, it runs at 26.6 FPS with 24.3 mAP. It achieves 23.3 mAP using just 8 parameters to represent the mask, which is double the amount of parameters to predict a bounding box. Code will be available at: github.com/cogsys-tuebingen/FourierNet.

READ FULL TEXT
research
10/15/2018

Instance Segmentation and Object Detection with Bounding Shape Masks

Many recent object detection algorithms use the bounding box regressor t...
research
09/29/2019

PolarMask: Single Shot Instance Segmentation with Polar Representation

In this paper, we introduce an anchor-box free and single shot instance ...
research
04/04/2019

YOLACT: Real-time Instance Segmentation

We present a simple, fully-convolutional model for real-time instance se...
research
12/03/2019

YOLACT++: Better Real-time Instance Segmentation

We present a simple, fully-convolutional model for real-time (>30 fps) i...
research
07/19/2022

Box-supervised Instance Segmentation with Level Set Evolution

In contrast to the fully supervised methods using pixel-wise mask labels...
research
06/23/2021

Real-time Instance Segmentation with Discriminative Orientation Maps

Although instance segmentation has made considerable advancement over re...
research
02/08/2022

SCR: Smooth Contour Regression with Geometric Priors

While object detection methods traditionally make use of pixel-level mas...

Please sign up or login with your details

Forgot password? Click here to reset