Pick of the Bunch: Detecting Infrared Small Targets Beyond Hit-Miss Trade-Offs via Selective Rank-Aware Attention

TL;DR

SeRankDet is a novel deep learning framework that significantly improves infrared small target detection by employing selective rank-aware attention, adaptive feature fusion, and dilated difference convolution, surpassing traditional trade-offs between detection accuracy and false alarms.

Contribution

The paper introduces SeRankDet, a lightweight network with innovative modules for selective attention, adaptive feature fusion, and enhanced target-background separation, advancing infrared small target detection.

Findings

Achieves state-of-the-art performance on multiple datasets.

Effectively balances detection precision and false alarm rates.

Demonstrates robustness in complex background scenarios.

Abstract

Infrared small target detection faces the inherent challenge of precisely localizing dim targets amidst complex background clutter. Traditional approaches struggle to balance detection precision and false alarm rates. To break this dilemma, we propose SeRankDet, a deep network that achieves high accuracy beyond the conventional hit-miss trade-off, by following the ``Pick of the Bunch'' principle. At its core lies our Selective Rank-Aware Attention (SeRank) module, employing a non-linear Top-K selection process that preserves the most salient responses, preventing target signal dilution while maintaining constant complexity. Furthermore, we replace the static concatenation typical in U-Net structures with our Large Selective Feature Fusion (LSFF) module, a dynamic fusion strategy that empowers SeRankDet with adaptive feature integration, enhancing its ability to discriminate true targets from false alarms. The network's discernment is further refined by our Dilated Difference Convolution (DDC) module, which merges differential convolution aimed at amplifying subtle target characteristics with dilated convolution to expand the receptive field, thereby substantially improving target-background separation. Despite its lightweight architecture, the proposed SeRankDet sets new benchmarks in state-of-the-art performance across multiple public datasets. The code is available at https://github.com/GrokCV/SeRankDet.