RSGMamba introduces a reliability-aware self-gated Mamba block for dynamic cross-modal feature selection in semantic segmentation, delivering state-of-the-art mIoU on RGB-D and RGB-T benchmarks with 48.6M parameters.
Ex- plicit attention-enhanced fusion for rgb-thermal perception tasks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
DSAFormer applies spatial and channel sparse multi-head cross-attention plus a learnable fusion block to reduce redundant token interactions and improve multispectral object detection on four public datasets.
citing papers explorer
-
RSGMamba: Reliability-Aware Self-Gated State Space Model for Multimodal Semantic Segmentation
RSGMamba introduces a reliability-aware self-gated Mamba block for dynamic cross-modal feature selection in semantic segmentation, delivering state-of-the-art mIoU on RGB-D and RGB-T benchmarks with 48.6M parameters.
-
Dual Sparse Aggregation Transformer for Multispectral Object Detection
DSAFormer applies spatial and channel sparse multi-head cross-attention plus a learnable fusion block to reduce redundant token interactions and improve multispectral object detection on four public datasets.