Semantic image segmentation typically relies on static pixel- wise classifiers that operate over a fixed category space, making them insensitive to the actual semantic composition of a real-world image. In this work, we propose CaSS, a category-aware semantic segmentation framework that introduces image-level semantic priors to dynamically adapt pixel-level classification. Specifically, a pre-trained vision–language model is employed to infer the set of semantic categories present in an image, which is encoded as a structured category prior. This prior is then used to drive a lightweight dynamic parsing network that generates image-conditioned classifier parameters for pixel- wise segmentation. By explicitly constraining the classifier with category-aware priors, CaSS reduces interference from absent classes and enhances both intra-class consistency and inter-class discriminability. The proposed approach follows a large–small model collaboration paradigm, leveraging the strong semantic understanding of vision–language models while preserving efficient pixel-level inference. Extensive experiments on standard semantic segmentation benchmarks demonstrate that CaSS consistently improves segmentation accuracy over state-of-the-art methods with minimal parameter overhead.

Semi-supervised semantic segmentation has witnessed remarkable advancements in recent years. However, existing algorithms are based on convolutional neural networks, and directly applying them to Vision Transformers poses certain limitations due to conceptual disparities. To this end, we propose TokenSwap, a data augmentation technique designed explicitly for semi-supervised semantic segmentation with Vision Transformers. TokenSwap aligns well with the global attention mechanism by mixing images at the token level, enhancing the learning capability for contextual information among image patches and the utilization of unlabeled data. We further incorporate image augmentation and feature augmentation to promote the diversity of augmentation. Moreover, to enhance consistency regularization, we propose a dual-branch framework where each branch applies image and feature augmentation to the input image. We conduct extensive experiments across multiple benchmark datasets, including Pascal VOC 2012, Cityscapes, and COCO. Results suggest that the proposed method outperforms state-of-the-art algorithms with notably observed accuracy improvement, especially under limited fine annotations.

Emerging technological innovations introduce the possibility to reconfigure the data center topology at runtime. The development of reconfigurable architectures can adapt their topology to account for changing demands, e.g., using Flyways-like augmented links. However, there is no common notion established in this area of how to evaluate the topology, the underlying theoretical analysis is not yet well studied. In this paper, we present the upper bound of the network diameter using spectral graph theory, to the best of our knowledge, which is a first theoretical attempt on understanding the nature of the reconfigurable data center networks. We further prove the algebraic connectivity is insensitive to the weight changes. Finally, based the algebra-connectivity λ2, we give a comprehensive link-augmentation validity, which can be implemented in current DCNs potentially.