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 this https URL
Abstract (translated)
红外小目标检测(ISTD)在预警、救援和 guidance 等领域具有广泛的应用。然而,基于卷积神经网络的深度学习方法在分割红外小目标(IRST)方面效果不佳,因为它缺乏清晰的轮廓和纹理特征。Transformer 方法也由于卷积诱导偏差而无法取得显著结果。为了解决这些问题,我们提出了一种新模型,称为注意力具有双端相关性(ABC),它基于Transformer 架构,包括一个卷积线性融合Transformer(CLFT)模块,并配备了一种独特的注意力机制,用于特征提取和融合,有效地增强了目标特征,抑制了噪声。此外,我们的模型还包括一个U形卷积膨胀卷积(UCDC)模块,位于网络较深层的神经元中,利用较深特征的较小分辨率获取更精细的语义信息。公开数据集的实验结果表明,我们的 approach 取得了最先进的性能。代码可在 this https URL 中找到。
URL
https://arxiv.org/abs/2303.10321