2 papers
cs.CV2026
Accuracy Improvement of Semi-Supervised Segmentation Using Supervised ClassMix and Sup-Unsup Feature Discriminator
Takahiro Mano, Reiji Saito, Kazuhiro Hotta
In semantic segmentation, the creation of pixel-level labels for training data incurs significant costs. To address this problem, semi-supervised learning, which utilizes a small n…
cs.CV2025
Domain Generalization through Attenuation of Domain-Specific Information
Reiji Saito, Kazuhiro Hotta
In this paper, we propose a new evaluation metric called Domain Independence (DI) and Attenuation of Domain-Specific Information (ADSI) which is specifically designed for domain-ge…