Learning to segment from misaligned and partial labels

05/27/2020
by   Simone Fobi, et al.
0

To extract information at scale, researchers increasingly apply semantic segmentation techniques to remotely-sensed imagery. While fully-supervised learning enables accurate pixel-wise segmentation, compiling the exhaustive datasets required is often prohibitively expensive. As a result, many non-urban settings lack the ground-truth needed for accurate segmentation. Existing open source infrastructure data for these regions can be inexact and non-exhaustive. Open source infrastructure annotations like OpenStreetMaps (OSM) are representative of this issue: while OSM labels provide global insights to road and building footprints, noisy and partial annotations limit the performance of segmentation algorithms that learn from them. In this paper, we present a novel and generalizable two-stage framework that enables improved pixel-wise image segmentation given misaligned and missing annotations. First, we introduce the Alignment Correction Network to rectify incorrectly registered open source labels. Next, we demonstrate a segmentation model – the Pointer Segmentation Network – that uses corrected labels to predict infrastructure footprints despite missing annotations. We test sequential performance on the AIRS dataset, achieving a mean intersection-over-union score of 0.79; more importantly, model performance remains stable as we decrease the fraction of annotations present. We demonstrate the transferability of our method to lower quality data, by applying the Alignment Correction Network to OSM labels to correct building footprints; we also demonstrate the accuracy of the Pointer Segmentation Network in predicting cropland boundaries in California from medium resolution data. Overall, our methodology is robust for multiple applications with varied amounts of training data present, thus offering a method to extract reliable information from noisy, partial data.

READ FULL TEXT

page 1

page 3

page 5

page 6

page 7

page 8

research
06/21/2021

Distilling effective supervision for robust medical image segmentation with noisy labels

Despite the success of deep learning methods in medical image segmentati...
research
06/20/2019

A multi-task U-net for segmentation with lazy labels

The need for labour intensive pixel-wise annotation is a major limitatio...
research
01/21/2021

Rethinking Semantic Segmentation Evaluation for Explainability and Model Selection

Semantic segmentation aims to robustly predict coherent class labels for...
research
07/12/2018

Learning to Segment Medical Images with Scribble-Supervision Alone

Semantic segmentation of medical images is a crucial step for the quanti...
research
06/16/2022

Joint Class-Affinity Loss Correction for Robust Medical Image Segmentation with Noisy Labels

Noisy labels collected with limited annotation cost prevent medical imag...
research
06/03/2021

Noisy Labels are Treasure: Mean-Teacher-Assisted Confident Learning for Hepatic Vessel Segmentation

Manually segmenting the hepatic vessels from Computer Tomography (CT) is...
research
02/18/2020

Lake Ice Monitoring with Webcams and Crowd-Sourced Images

Lake ice is a strong climate indicator and has been recognised as part o...

Please sign up or login with your details

Forgot password? Click here to reset