APNet: Accurate Prompting Network With Modality Guidance and Structural Awareness for RGB-D Semantic Segmentation
IEEE Signal Processing Letters · 2026 · 33 · 2131-2135
DOI: 10.1109/lsp.2026.3693589 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Junzhe Zhao und 4 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben.
Abstract (Originalsprache)
Parameter-efficient fine-tuning (PEFT) is promising for RGB-D semantic segmentation, as lightweight prompters enable frozen pre-trained RGB backbones to leverage massive RGB pretraining knowledge without full fine-tuning on limited paired RGB-D data. However, existing PEFT methods have two critical limitations: static modal fusion ignores the dynamic reliability of RGB and depth across scenes, leading to suboptimal performance in complex environments; conventional prompts lack structural awareness, causing the loss of edge and texture details essential for dense prediction. To solve these problems, we propose the Accurate Prompting Network (APNet) for precise prompt injection in frozen backbones with two core modules. A Modality Effectiveness Guider (MEG) conducts input-level modal reliability assessment and dynamically generates scene-adaptive modality weights by capturing scene characteristics (e.g., illumination, texture richness). A Structural Awareness Prompter (SAP) injects directional structural priors into prompts via multi-directional gating convolution, endowing prompts with explicit edge and texture information to match semantic segmentation demands. MEG and SAP collaboratively form a precise prompting mechanism that realizes dynamic modal contribution allocation and structural detail preservation, facilitating efficient and accurate cross-modal knowledge transfer to the frozen backbone. Extensive experiments on NYUDv2 and SUN RGB-D show that APNet achieves state-of-the-art mIoU of 59.6% and 52.6% with only 6.2 M trainable parameters, realizing a superior trade-off between segmentation accuracy and parameter efficiency.
Zitieren
APA
Zhao, J., Su, J., Liu, J., Wang, M., & Liu, Y. (2026). APNet: Accurate Prompting Network With Modality Guidance and Structural Awareness for RGB-D Semantic Segmentation. IEEE Signal Processing Letters, 33, 2131-2135. https://doi.org/10.1109/lsp.2026.3693589
Vancouver
Zhao J, Su J, Liu J, Wang M, Liu Y. APNet: Accurate Prompting Network With Modality Guidance and Structural Awareness for RGB-D Semantic Segmentation. IEEE Signal Processing Letters. 2026;33:2131-2135. doi:10.1109/lsp.2026.3693589
BibTeX
@article{Zhao2026,
author = {Zhao, Junzhe and Su, Jintao and Liu, Jun and Wang, Miaohui and Liu, Ye},
title = {APNet: Accurate Prompting Network With Modality Guidance and Structural Awareness for RGB-D Semantic Segmentation},
journal = {IEEE Signal Processing Letters},
year = {2026},
volume = {33},
pages = {2131--2135},
doi = {10.1109/lsp.2026.3693589}
}
EUVIMED