2023 · 24 citations · 35 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionImage ClassificationImage LabelingPattern RecognitionSemantic SegmentationSemi-supervised LearningSupervised LearningFuzzy SetsInterferenceInterference SuppressionPlug-and-play ModulesPseudo-labelingRegularizationSemi-supervised SegmentationSemi-supervised Semantic Segmentation
Semi-supervised learning (SSL) essentially pursues class boundary exploration with less dependence on human annotations. Although typical attempts focus on ameliorating the inevitable error-prone pseudo-labeling, we think differently and resort to exhausting informative semantics from multiple probably correct candidate labels. In this paper, we introduce Fuzzy Positive Learning (FPL) for accurate SSL semantic segmentation in a plug-and-play fashion, targeting adaptively encouraging fuzzy positive predictions and suppressing highly-probable negatives. Being conceptually simple yet practically effective, FPL can remarkably alleviate interference from wrong pseudo labels and progressively achieve clear pixel-level semantic discrimination. Concretely, our FPL approach consists of two main components, including fuzzy positive assignment (FPA) to provide an adaptive number of labels for each pixel and fuzzy positive regularization (FPR) to restrict the predictions of fuzzy positive categories to be larger than the rest under different perturbations. Theoretical analysis and extensive experiments on Cityscapes and VOC 2012 with consistent performance gain justify the superiority of our approach. Codes are provided in https://github.com/qpc1611094/FPL.
35
The Cityscapes Dataset for Semantic Urban Scene Understanding
Marius Cordts, Mohamed Omran, Sebastian Ramos et al. · 2016 · 11.9K citations
Deep Sparse Rectifier Neural Networks
Xavier Glorot, Antoine Bordes, Yoshua Bengio · 2012 · 5.4K citations
SphereFace: Deep Hypersphere Embedding for Face Recognition
Weiyang Liu, Yandong Wen, Zhiding Yu et al. · 2017 · 3K citations
CosFace: Large Margin Cosine Loss for Deep Face Recognition
Hao Wang, Yitong Wang, Zheng Zhou et al. · 2018 · 2.9K citations