Active Learning for Delineation of Curvilinear Structures

Mosinska-Domanska, Agata; Sznitman, Raphael; Głowacki, Przemysław; Fua, Pascal

doi:10.1109/cvpr.2016.565

Cited by 10 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Only a minimum number of data fulfilling both criterions were selected and annotated by a human expert. Mosinska et al . tailored the uncertainty sampling‐based active learning approach for the delineation of complex linear structures problem, which significantly reduced the size (up to 80%) of training dataset while achieving equivalent performance.…”

Section: Expanding Datasets For Deep Learningmentioning

confidence: 99%

Deep learning in medical imaging and radiation therapy

et al. 2018

View full text Add to dashboard Cite

The goals of this review paper on deep learning (DL) in medical imaging and radiation therapy are to (a) summarize what has been achieved to date; (b) identify common and unique challenges, and strategies that researchers have taken to address these challenges; and (c) identify some of the promising avenues for the future both in terms of applications as well as technical innovations. We introduce the general principles of DL and convolutional neural networks, survey five major areas of application of DL in medical imaging and radiation therapy, identify common themes, discuss methods for dataset expansion, and conclude by summarizing lessons learned, remaining challenges, and future directions.

show abstract

Section: Expanding Datasets For Deep Learningmentioning

confidence: 99%

Deep learning in medical imaging and radiation therapy

et al. 2018

View full text Add to dashboard Cite

show abstract

“…In this case the maximally informative labelled-pixel subset is the one which yields the lowest generalization error when used to train a supervised semantic segmentation model. Prior work targetting segmentation has investigated strategies to select superpixels that induce the maximum label change for a CRF on the training set by using weak (image-level category) supervision [71], incorporate geometric constraints [34,47] and propagate foreground masks to large-scale image collections [28]. For foreground segmentation of medical imagery, FCNs [44] have been cou-pled with bootsrapping [77], and U-Nets [55] with dropoutbased Monte Carlo estimates of uncertainty [22] to drive label acquisition via uncertainty sampling.…”

Section: Related Workmentioning

confidence: 99%

All you need are a few pixels: semantic segmentation with PixelPick

Shin¹,

Xie²,

Albanie³

2021

Preprint

View full text Add to dashboard Cite

A central challenge for the task of semantic segmentation is the prohibitive cost of obtaining dense pixel-level annotations to supervise model training. In this work, we show that in order to achieve a good level of segmentation performance, all you need are a few well-chosen pixel labels.We make the following contributions: (i) We investigate the semantic segmentation setting in which labels are supplied only at sparse pixel locations, and show that deep neural networks can use a handful of such labels to good effect; (ii) We demonstrate how to exploit this phenomena within an active learning framework, termed PIXELPICK, to radically reduce labelling cost, and propose an efficient "mouse-free" annotation strategy to implement our approach; (iii) We conduct extensive experiments to study the influence of annotation diversity under a fixed budget, model pretraining, model capacity and the sampling mechanism for picking pixels in this low annotation regime; (iv) We provide comparisons to the existing state of the art in semantic segmentation with active learning, and demonstrate comparable performance with up to two orders of magnitude fewer pixel annotations on the CAMVID, CITYSCAPES and PASCAL VOC 2012 benchmarks; (v) Finally, we evaluate the efficiency of our annotation pipeline and its sensitivity to annotator error to demonstrate its practicality.

show abstract

“…Only a minimum number of data fulfilling both criterions were selected and annotated by a human expert. Mosinska et al 344 tailored the uncertainty sampling-based active learning approach for the delineation of complex linear structures problem, which significantly reduced the size (up to 80%) of training dataset while achieving equivalent performance. Multiple samples inside the same image were simultaneously presented to the annotator while the interactive annotation framework kept the selected samples informative, representative, and diverse.…”

Section: C Data Annotation Via Active Learningmentioning

confidence: 99%