MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority Maps

10/05/2020
by   Pascal Colling, et al.
0

We present a novel region based active learning method for semantic image segmentation, called MetaBox+. For acquisition, we train a meta regression model to estimate the segment-wise Intersection over Union (IoU) of each predicted segment of unlabeled images. This can be understood as an estimation of segment-wise prediction quality. Queried regions are supposed to minimize to competing targets, i.e., low predicted IoU values / segmentation quality and low estimated annotation costs. For estimating the latter we propose a simple but practical method for annotation cost estimation. We compare our method to entropy based methods, where we consider the entropy as uncertainty of the prediction. The comparison and analysis of the results provide insights into annotation costs as well as robustness and variance of the methods. Numerical experiments conducted with two different networks on the Cityscapes dataset clearly demonstrate a reduction of annotation effort compared to random acquisition. Noteworthily, we achieve 95 (mIoU), using MetaBox+ compared to when training with the full dataset, with only 10.47

READ FULL TEXT

page 2

page 4

page 5

page 6

page 7

research
10/23/2018

CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation

State of the art methods for semantic image segmentation are trained in ...
research
07/13/2020

On uncertainty estimation in active learning for image segmentation

Uncertainty estimation is important for interpreting the trustworthiness...
research
11/26/2019

ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation

We propose ViewAL, a novel active learning strategy for semantic segment...
research
07/26/2023

Hybrid Representation-Enhanced Sampling for Bayesian Active Learning in Musculoskeletal Segmentation of Lower Extremities

Purpose: Obtaining manual annotations to train deep learning (DL) models...
research
09/17/2023

Active Learning for Semantic Segmentation with Multi-class Label Query

This paper proposes a new active learning method for semantic segmentati...
research
07/17/2018

A Deep Learning Driven Active Framework for Segmentation of Large 3D Shape Collections

High-level shape understanding and technique evaluation on large reposit...
research
09/23/2021

Active Learning for Argument Strength Estimation

High-quality arguments are an essential part of decision-making. Automat...

Please sign up or login with your details

Forgot password? Click here to reset