The paper introduces SIFR, a frequency-aware dual‑stream framework for domain‑generalized semantic segmentation. SIFR performs spectral‑guided invariant fusion of frozen CLIP and DINOv2 features to suppress domain‑sensitive responses while preserving semantic and structural cues, and adds a spectral decoder refinement module that normalizes low‑frequency statistics and adaptively selects frequencies to reduce residual domain bias. Experiments on synthetic‑to‑real, real‑to‑real, and adverse‑weather benchmarks show consistent improvements over prior state‑of‑the‑art methods.
By Yansong Bai, Yunzhi Zhuge, Xinzhuo Yu, Lu Zhang, Jin Zhan, Pingping Zhang, Huchuan Lu
Frequency-domain information is beneficial for semantic segmentation. However, existing frequency-based methods often suffer from insufficient frequency utilization, inefficient fusion, and high compu...
arXiv:2610.34734v1 Announce Type: new
Abstract: Frequency-domain information is beneficial for semantic segmentation. However, existing frequency-based methods often suffer from insufficient frequenc...
By Xiaofan Yang, Wei Pan, Yubin Liu, Junyu Wu, Junming Zhang, Jie Zhao
arXiv:2606.08906v2 Announce Type: replace
Abstract: In many binary segmentation tasks, most multimodal methods rely on fixed feature concatenation for cross-modal interaction and straightforward deco...
By Qiangqiang Zhou, Jiawei Xu, Yong Chen, Dandan Zhu, Yugen Yi, Xiaoqi Zhao
Open-vocabulary remote sensing segmentation has recently emerged as a promising paradigm that enables pixel-level recognition of arbitrary categories specified by natural language, including classes unseen during training. However, geospatial domain shifts caused by heterogeneous regions, spatial resolutions, and acquisition platforms weaken visual-text matching and limit cross-dataset generalization.
arXiv:2610.35374v1 Announce Type: new
Abstract: Single-Domain Generalized Object Detection (S-DGOD) aims to generalize from a single source domain to unseen domains under distribution shifts. Existin...
By Yin Zhang, Yaoyue Zheng, Yongqiang Zhang, Bogdan Raducanu, Dan Li