Effective Receptive Field Ordering Matters for Infrared Small Target Detection
2026-07-27 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors studied how the arrangement of effective receptive fields (ERFs) inside neural networks affects detecting small targets in infrared images. They found that not just the size but the order and organization of these ERFs change how features are refined during detection. Using this idea, they created a new model called RFONet that organizes ERFs in a special sequence to improve accuracy and speed. Their method also handles noise and variations well, making it reliable across different datasets. This work offers new theory and designs for better managing how neural networks process visual information.
Effective Receptive FieldInfrared Small Target DetectionFeature RefinementResidual CorrectionScale-Frequency CorrespondenceNonlinear Non-CommutativityConvolutional Neural NetworksMultigrid V-cycleNoise RobustnessCross-Dataset Generalization
Authors
Guoyi Zhang, Yanjin Du, Zhengyao Zhao, Tongsu Zhang, Guangsheng Xu, Siyang Chen, Xiangpeng Xu, Han Wang, Xiaohu Zhang
Abstract
In this work, we investigate a previously unexplored architectural dimension for infrared small target detection: the organization of effective receptive fields (ERFs) during feature refinement. Unlike existing approaches that primarily improve individual feature operators, we argue that ERF organization constitutes an architectural dimension independent of receptive field design itself, and formulate deep feature transformation as a progressive residual correction process, from which a theoretical framework for ERF scheduling is established. Specifically, we reveal that ERF refinement is governed by two fundamental properties: scale-frequency correspondence, which aligns different ERF scales with distinct residual frequency characteristics, and nonlinear non-commutativity, which makes different ERF orderings produce fundamentally different refinement trajectories. Together, these properties show that ERF organization, rather than ERF scale alone, governs refinement dynamics. Guided by these principles, we propose Receptive Field Ordering Network (RFONet), which realizes hierarchical ERF scheduling through a multigrid-inspired V-cycle strategy using only standard $3\times3$ convolutions. RFONet achieves state-of-the-art performance on multiple benchmarks with only 1.16M parameters and over 157 FPS inference speed. Beyond empirical performance, our theoretical analysis provides theoretical guarantees for stable residual refinement under perturbations, frequency shifts, and partial occlusions, which are consistently reflected in superior noise robustness and cross-dataset generalization. Finally, our framework reformulates ERF organization as a task-dependent optimization objective, providing a principled foundation for future adaptive receptive field scheduling.