ABC: Attention with Bilinear Correlation for Infrared Small Target Detection

TL;DR

This paper introduces ABC, a novel transformer-based model with convolutional modules for infrared small target detection, significantly improving accuracy by enhancing target features and reducing noise.

Contribution

The paper proposes a new attention mechanism and a convolution-dilated module within a transformer architecture to improve infrared small target detection performance.

Findings

Achieves state-of-the-art results on public datasets.

Effectively enhances target features and suppresses noise.

Outperforms existing CNN and transformer-based methods.

Abstract

Infrared small target detection (ISTD) has a wide range of applications in early warning, rescue, and guidance. However, CNN based deep learning methods are not effective at segmenting infrared small target (IRST) that it lack of clear contour and texture features, and transformer based methods also struggle to achieve significant results due to the absence of convolution induction bias. To address these issues, we propose a new model called attention with bilinear correlation (ABC), which is based on the transformer architecture and includes a convolution linear fusion transformer (CLFT) module with a novel attention mechanism for feature extraction and fusion, which effectively enhances target features and suppresses noise. Additionally, our model includes a u-shaped convolution-dilated convolution (UCDC) module located deeper layers of the network, which takes advantage of the smaller resolution of deeper features to obtain finer semantic information. Experimental results on public datasets demonstrate that our approach achieves state-of-the-art performance. Code is available at https://github.com/PANPEIWEN/ABC