Elucidating Meta-Structures of Noisy Labels in Semantic Segmentation by Deep Neural Networks
Supervised training of deep neural networks (DNNs) by noisy labels has been studied extensively in image classification but much less in image segmentation. Our understanding of the learning behavior of DNNs trained by noisy segmentation labels remains limited. We address this deficiency in both binary segmentation of biological microscopy images and multi-class segmentation of natural images. We classify segmentation labels according to their noise transition matrices (NTMs) and compare performance of DNNs trained by different types of labels. When we randomly sample a small fraction (e.g., 10%) or flip a large fraction (e.g., 90%) of the ground-truth labels to train DNNs, their segmentation performance remains largely unchanged. This indicates that DNNs learn structures hidden in labels rather than pixel-level labels per se in their supervised training for semantic segmentation. We call these hidden structures meta-structures. When labels with different perturbations to the meta-structures are used to train DNNs, their performance in feature extraction and segmentation degrades consistently. In contrast, addition of meta-structure information substantially improves performance of an unsupervised model in binary semantic segmentation. We formulate meta-structures mathematically as spatial density distributions. We show theoretically and experimentally how this formulation explains key observed learning behavior of DNNs.
Code (1)
Tasks
image-classificationImage ClassificationImage SegmentationSegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Deep Neural Networks Learn Meta-Structures from Noisy Labels in Semantic Segmentation
How deep neural networks (DNNs) learn from noisy labels has been studied extensively in image classification but much less in image segmentation. So far, our understanding of the learning behavior of DNNs trained by nois…
image-classificationImage ClassificationImage SegmentationSegmentation+1CLID-MU: Cross-Layer Information Divergence Based Meta Update Strategy for Learning with Noisy Labels
Learning with noisy labels (LNL) is essential for training deep neural networks with imperfect data. Meta-learning approaches have achieved success by using a clean unbiased labeled set to train a robust model. However, …
Learning with noisy labelsMeta-LearningWebly Supervised Image Classification with Metadata: Automatic Noisy Label Correction via Visual-Semantic Graph
Webly supervised learning becomes attractive recently for its efficiency in data expansion without expensive human labeling. However, adopting search queries or hashtags as web labels of images for training brings massiv…
General ClassificationGraph Neural Networkimage-classificationImage Classification+2MetaSeg: Content-Aware Meta-Net for Omni-Supervised Semantic Segmentation
Noisy labels, inevitably existing in pseudo segmentation labels generated from weak object-level annotations, severely hampers model optimization for semantic segmentation. Previous works often rely on massive hand-craft…
Meta-LearningModel OptimizationSegmentationSemantic SegmentationMeta Soft Label Generation for Noisy Labels
The existence of noisy labels in the dataset causes significant performance degradation for deep neural networks (DNNs). To address this problem, we propose a Meta Soft Label Generation algorithm called MSLG, which can j…
Meta-Learning