Work

Reliability gated cross-modal attention with shear reparameterized directional reasoning for RGB-thermal salient object detection

Year: 2026

Type: article

Abstract: RGB-Thermal (RGB-T) salient object detection localizes salient regions where appearance cues alone are insufficient, since thermal radiation stays informative under poor illumination. Two limitations persist. Cross-modal attention is applied at a strength fixed in advance, so a momentarily uninformative stream continues to contribute in full, and directional reasoning is confined to the two image axes, because diagonal coverage has required a dense affinity mask of quadratic cost. We present CDRNet, a Confidence and Directional Reasoning Network with dual ResNet-50 encoders. Cross-modal attention is reliability-gated: a coefficient estimated for each modality from spatial entropy and gradient energy scales the transferred context through a gated residual, and the attention scale is derived from the cosine discrepancy between the pooled modality embeddings, so sharpness follows the semantic gap instead of a fixed constant, and balanced inputs recover symmetric fusion. Directional reasoning is shear-reparameterized: a circular shear maps each diagonal onto an axis, so a single axial operator covers four orientations at axial rather than quadratic cost, a per-pixel gate exposes the learned anisotropy, and a weight-shared second stage refines the result without additional parameters. A boundary gated decoder returns edge evidence to the representation through multiplicative modulation under auxiliary supervision, and its cross scale aggregator mixes two dilation rates per branch under context-dependent weights. On VT821, VT1000, and VT5000, CDRNet attains S-measure values of 0.908, 0.949, and 0.918, surpasses 19 recent methods on all metrics, and ablations isolate each contribution.

Source: Scientific Reports

DOI: 10.1038/s41598-026-72418-w

Authors: Kamal M. Othman, Abdulfattah Noorwali, Manal Abdullah Alohali, Inam Ullah, Mi Young Lee

Institutions: Umm al-Qura University, Princess Nourah bint Abdulrahman University, Gachon University, Chung-Ang University

Language: English

Topic: Visual Attention and Saliency Detection

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,690

Funders: National Research Foundation of Korea, Princess Nourah Bint Abdulrahman University, Ministry of Science and ICT, South Korea, Deanship of Scientific Research, Princess Nourah Bint Abdulrahman University