Inter and Intra-Domain Mixing for Improved Semi-Supervised Domain Adaptation in Semantic Segmentation
The proposed Inter and Intra-Domain Mixing (IIDM) framework effectively leverages both inter-domain and intra-domain information to mitigate the domain shift and enhance the performance of semi-supervised domain adaptation in semantic segmentation.
Enhancing Semantic Segmentation Performance with Convolution-based Probability Gradient Loss
The paper introduces a novel Convolution-based Probability Gradient (CPG) loss function that enhances the performance of semantic segmentation networks by maximizing the similarity between the predicted and ground-truth probability gradients, particularly at object boundaries.
Decouple Defogging and Semantic Learning for Improved Foggy Domain-Adaptive Segmentation
A novel training framework, Decouple Defogging and Semantic learning (D2SL), that learns better semantics for segmentation while maintaining defogging ability by decoupling defogging and semantic learning tasks.
Hierarchical Semantic Segmentation: Limitations and Opportunities in Hyperbolic Geometry
The core message of this article is that the established practice of hierarchical semantic segmentation may be limited to in-domain settings, whereas flat classifiers generalize substantially better, especially if they are modeled in the hyperbolic space.
ECAP: Extensive Cut-and-Paste Augmentation for Unsupervised Domain Adaptive Semantic Segmentation
ECAP proposes a novel data augmentation strategy to reduce the impact of erroneous pseudo-labels in unsupervised domain adaptive semantic segmentation.
ECAP: Extensive Cut-and-Paste Augmentation for Unsupervised Domain Adaptive Semantic Segmentation
提案されたECAPは、信頼性の高い疑似ラベルを活用することで、誤った疑似ラベルの影響を軽減し、セマンティックセグメンテーションの未監督ドメイン適応におけるパフォーマンスを向上させます。
© 2024 by Linnk AI