Subpixel object segmentation using wavelets and multi resolution analysis

10/28/2021
by   Ray Sheombarsing, et al.
0

We propose a novel deep learning framework for fast prediction of boundaries of two-dimensional simply connected domains using wavelets and Multi Resolution Analysis (MRA). The boundaries are modelled as (piecewise) smooth closed curves using wavelets and the so-called Pyramid Algorithm. Our network architecture is a hybrid analog of the U-Net, where the down-sampling path is a two-dimensional encoder with learnable filters, and the upsampling path is a one-dimensional decoder, which builds curves up from low to high resolution levels. Any wavelet basis induced by a MRA can be used. This flexibility allows for incorporation of priors on the smoothness of curves. The effectiveness of the proposed method is demonstrated by delineating boundaries of simply connected domains (organs) in medical images using Debauches wavelets and comparing performance with a U-Net baseline. Our model demonstrates up to 5x faster inference speed compared to the U-Net, while maintaining similar performance in terms of Dice score and Hausdorff distance.

READ FULL TEXT

page 8

page 14

page 18

research
05/06/2020

CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement

State-of-the-art semantic segmentation methods were almost exclusively t...
research
06/25/2019

MFP-Unet: A Novel Deep Learning Based Approach for Left Ventricle Segmentation in Echocardiography

Segmentation of the Left ventricle (LV) is a crucial step for quantitati...
research
06/27/2018

3D RoI-aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation

Objective: Segmentation of colorectal cancerous regions from the Magneti...
research
11/29/2022

Fourier-Net: Fast Image Registration with Band-limited Deformation

Unsupervised image registration commonly adopts U-Net style networks to ...
research
02/27/2020

Coronary Wall Segmentation in CCTA Scans via a Hybrid Net with Contours Regularization

Providing closed and well-connected boundaries of coronary artery is ess...
research
03/25/2020

DeepStrip: High Resolution Boundary Refinement

In this paper, we target refining the boundaries in high resolution imag...
research
01/19/2023

A Multi-Resolution Framework for U-Nets with Applications to Hierarchical VAEs

U-Net architectures are ubiquitous in state-of-the-art deep learning, ho...

Please sign up or login with your details

Forgot password? Click here to reset