Maturity-Aware Active Learning for Semantic Segmentation with Hierarchically-Adaptive Sample Assessment
Not on the map. Why?
Abstract (arXiv)
Active Learning (AL) for semantic segmentation is challenging due to heavy class imbalance and different ways of defining "sample" (pixels, areas, etc.), leaving the interpretation of the data distribution ambiguous. We propose "Maturity-Aware Distribution Breakdown-based Active Learning'' (MADBAL), an AL method that benefits from a hierarchical approach to define a multiview data distribution, which takes into account the different "sample" definitions jointly, hence able to select the most impactful segmentation pixels with comprehensive understanding. MADBAL also features a novel uncertainty formulation, where AL supporting modules are included to sense the features' maturity whose weighted influence continuously contributes to the uncertainty detection. In this way, MADBAL makes significant performance leaps even in the early AL stage, hence reducing the training burden significantly. It outperforms state-of-the-art methods on Cityscapes and PASCAL VOC datasets as verified in our extensive experiments.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 47 references that are in the map. First posted on arXiv 28 Aug 2023.
Builds on
31 of 47 references.
References · 31
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
- 2019Searching for MobileNetV3cited by 1,994
- 2017Deep Bayesian Active Learning with Image Datacited by 819
- 2020Image Segmentation Using Deep Learning: A Surveycited by 660
- 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
- 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
- 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 376
- 2019Learning Loss for Active Learningcited by 336
- 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 331
19 more
- 2019Variational Adversarial Active Learningcited by 284
- 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
- 2019FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inferencecited by 162
- 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 146
- 2018Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentationcited by 145
- 2017Learning Active Learning from Datacited by 101
- 2019ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentationcited by 96
- 2013SEEDS: Superpixels Extracted via Energy-Driven Samplingcited by 75
- 2019Active Learning for Deep Detection Neural Networkscited by 62
- 2020Reinforced active learning for image segmentationcited by 56
- 2018CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentationcited by 49
- 2017Cost-Effective Active Learning for Melanoma Segmentationcited by 41
- 2020DEAL: Difficulty-aware Active Learning for Semantic Segmentationcited by 32
- 2021All you need are a few pixels: semantic segmentation with PixelPickcited by 31
- 2021NTIRE 2021 Depth Guided Image Relighting Challengecited by 23
- 2020Importance of Self-Consistency in Active Learning for Semantic Segmentationcited by 21
- 2021CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentationcited by 6
- 2021Simultaneous Denoising and Localization Network for Photoacoustic Target Localizationcited by 5
- 2020Group Based Deep Shared Feature Learning for Fine-grained Image Classificationcited by 4
Built on by
Not cited yet.