Boundary as Barrier: Boundary-Guided Coherence Refinement for Robust Semantic Segmentation
IEEE Signal Processing Letters · 2026 · 33 · 2480-2484
DOI: 10.1109/lsp.2026.3698381 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Jin Liu und 6 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben.
Abstract (Originalsprache)
Semantic segmentation under adverse imaging conditions such as low illumination and motion blur often breaks into holes, fragments, and disconnected regions. Naive smoothing can reduce these artifacts, but it also tends to leak labels across true boundaries. We address this coherence–leakage dilemma with a plug-and-play decode-head refinement composed of a Multi-scale Boundary Detector (MBD) and a Boundary-Barrier Coherence Refiner (BBCR). MBD predicts a boundary probability map, and BBCR turns it into a soft barrier for logit-space refinement through prototype-based global coherence and barrier-gated local affinity propagation. Targeting mixed-condition deployments, where favorable and adverse inputs are interleaved, the proposed modules attach to existing segmentation heads without modifying backbones or necks. Across eight architectures on a binary dairy-farm dataset, our method improves mIoU by 0.97 points on average and by up to 13.35 points on a manually annotated low-light/blur stress-test split without target-domain fine-tuning. On NightCity with 19 classes, it further yields a consistent average gain of 0.96 mIoU points while preserving performance under favorable conditions.
Zitieren
APA
Liu, J., Yao, L., Hong, W., Ma, Y., Kong, F., Lei, L., & Fan, Z. (2026). Boundary as Barrier: Boundary-Guided Coherence Refinement for Robust Semantic Segmentation. IEEE Signal Processing Letters, 33, 2480-2484. https://doi.org/10.1109/lsp.2026.3698381
Vancouver
Liu J, Yao L, Hong W, Ma Y, Kong F, Lei L, et al. Boundary as Barrier: Boundary-Guided Coherence Refinement for Robust Semantic Segmentation. IEEE Signal Processing Letters. 2026;33:2480-2484. doi:10.1109/lsp.2026.3698381
BibTeX
@article{Liu2026,
author = {Liu, Jin and Yao, Lei and Hong, Weinan and Ma, Yuanqian and Kong, Fanrong and Lei, Lin and Fan, Zipei},
title = {Boundary as Barrier: Boundary-Guided Coherence Refinement for Robust Semantic Segmentation},
journal = {IEEE Signal Processing Letters},
year = {2026},
volume = {33},
pages = {2480--2484},
doi = {10.1109/lsp.2026.3698381}
}
EUVIMED