Learning Dynamic Local Context Representations for Infrared Small Target Detection

TL;DR

LCRNet is a novel model for infrared small target detection that effectively captures local context using dynamic representations, outperforming existing methods in accuracy and efficiency.

Contribution

The paper introduces LCRNet, a hybrid model with three innovative components that improve local context learning for infrared small target detection, reducing complexity and enhancing performance.

Findings

LCRNet achieves state-of-the-art detection accuracy.

LCRNet uses only 1.65 million parameters, demonstrating high efficiency.

Experiments show LCRNet outperforms 33 SOTA methods across multiple datasets.

Abstract

Infrared small target detection (ISTD) is challenging due to complex backgrounds, low signal-to-clutter ratios, and varying target sizes and shapes. Effective detection relies on capturing local contextual information at the appropriate scale. However, small-kernel CNNs have limited receptive fields, leading to false alarms, while transformer models, with global receptive fields, often treat small targets as noise, resulting in miss-detections. Hybrid models struggle to bridge the semantic gap between CNNs and transformers, causing high complexity.To address these challenges, we propose LCRNet, a novel method that learns dynamic local context representations for ISTD. The model consists of three components: (1) C2FBlock, inspired by PDE solvers, for efficient small target information capture; (2) DLC-Attention, a large-kernel attention mechanism that dynamically builds context and reduces feature redundancy; and (3) HLKConv, a hierarchical convolution operator based on large-kernel decomposition that preserves sparsity and mitigates the drawbacks of dilated convolutions. Despite its simplicity, with only 1.65M parameters, LCRNet achieves state-of-the-art (SOTA) performance.Experiments on multiple datasets, comparing LCRNet with 33 SOTA methods, demonstrate its superior performance and efficiency.