Authors:
Pascal Colling
1
;
2
;
Lutz Roese-Koerner
1
;
Hanno Gottschalk
2
and
Matthias Rottmann
2
Affiliations:
1
Aptiv, Wuppertal, Germany
;
2
University of Wuppertal, School of Mathematics and Natural Sciences, IMACM & IZMD, Germany
Keyword(s):
Active Learning, Semantic Segmentation, Priority Maps via Meta Regression, Cost Estimation.
Abstract:
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% of the mean Intersection
over Union (mIoU), using MetaBox+ compared to when training with the full dataset, with only 10.47% /
32.01% annotation effort for the two networks, respectively
(More)