Active Learning with Bayesian UNet for Efficient Semantic Image Segmentation
Isah Charles Saidu, Lehel Csató
Abstract
We present a sample-efficient image segmentation method using active learning, we call it Active Bayesian UNet, or AB-UNet. This is a convolutional neural network using batch normalization and max-pool dropout. The Bayesian setup is achieved by exploiting the probabilistic extension of the dropout mechanism, leading to the possibility to use the uncertainty inherently present in the system. We set up our experiments on various medical image datasets and highlight that with a smaller annotation effort our AB-UNet leads to stable training and better generalization. Added to this, we can efficiently choose from an unlabelled dataset.
Topics & Concepts
Computer scienceArtificial intelligenceDropout (neural networks)Normalization (sociology)Convolutional neural networkSegmentationMachine learningBayesian probabilityGeneralizationPattern recognition (psychology)Probabilistic logicAnnotationImage (mathematics)Image segmentationBayesian networkMathematicsMathematical analysisAnthropologySociologyMachine Learning and AlgorithmsDomain Adaptation and Few-Shot LearningMachine Learning and Data Classification