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

by   Pascal Colling, et al.

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



There are no comments yet.


page 2

page 4

page 5

page 6

page 7


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

State of the art methods for semantic image segmentation are trained in ...

On uncertainty estimation in active learning for image segmentation

Uncertainty estimation is important for interpreting the trustworthiness...

ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation

We propose ViewAL, a novel active learning strategy for semantic segment...

False Positive Detection and Prediction Quality Estimation for LiDAR Point Cloud Segmentation

We present a novel post-processing tool for semantic segmentation of LiD...

Spectral Analysis for Semantic Segmentation with Applications on Feature Truncation and Weak Annotation

The current neural networks for semantic segmentation usually predict th...

Active Learning for Argument Strength Estimation

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

Failure-averse Active Learning for Physics-constrained Systems

Active learning is a subfield of machine learning that is devised for de...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.