提案されたAllSparkは、ラベル付きデータを再生するためにラベルなしの特徴を活用し、既存の方法を凌駕します。
AllSpark verbessert die Semi-Supervised Semantic Segmentation durch die Wiedergeburt von markierten Merkmalen aus unmarkierten Merkmalen.
The core message of this paper is to propose two efficient semi-supervised learning architectures, DiverseHead and DiverseModel, that leverage multi-head and multi-model approaches to enhance the precision and diversity of pseudo labels during training, leading to improved semantic segmentation performance on remote sensing imagery datasets.
The proposed Dual-Level Siamese Structure Network (DSSN) effectively leverages both labeled and unlabeled data to improve semi-supervised semantic segmentation performance, by utilizing dual-level contrastive learning and a novel class-aware pseudo-label generation strategy.