当前位置: X-MOL 学术Mach. Vis. Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
EAF-Net: an enhancement and aggregation–feedback network for RGB-T salient object detection
Machine Vision and Applications ( IF 2.4 ) Pub Date : 2022-07-12 , DOI: 10.1007/s00138-022-01312-y
Haiyang He , Jing Wang , Xiaolin Li , Minglin Hong , Shiguo Huang , Tao Zhou

Salient object detection (SOD) aims at highlighting important foreground objects automatically from the background. Most existing SOD methods only employ visible images (RGB images) for salient detection, which limits the performance of real-life applications when encountering challenging scenarios such as low illumination, haze, and smog. In this paper, we take advantage of the RGB and thermal images and propose an Enhancement and Aggregation–Feedback Network (EAF-Net) for SOD. Specifically, to achieve effective complementation between modalities and prevent the interference from noises, we first treat RGB and thermal images equally in the Feature Enhancement Block (FEB), and further, the Global Context Module expands receptive field to obtain the global features and the Top-Feature Enhancement Module suppresses the redundant information that may destroy the original features from the top layer. Subsequently, we embed several Cross Feature Aggregation Modules (CFAMs) into the Aggregation-and-Feedback Decoder to fuse different level features and compensation features for further obtaining comprehensive feature expression. Moreover, a feedback mechanism is adopted to propagate these fused features back into previous layers for refinement and generate saliency maps to decode features in a progressive way. Comprehensive experiments on RGB-T datasets demonstrate that EAF-Net achieves outstanding performance against the state-of-the-art models.



中文翻译:

EAF-Net:用于 RGB-T 显着目标检测的增强和聚合反馈网络

显着对象检测 (SOD) 旨在从背景中自动突出显示重要的前景对象。大多数现有的 SOD 方法仅使用可见图像(RGB 图像)进行显着检测,这限制了现实应用在遇到低照度、雾霾和烟雾等具有挑战性的场景时的性能。在本文中,我们利用 RGB 和热图像,提出了一种用于 SOD 的增强和聚合反馈网络 (EAF-Net)。具体来说,为了实现模态之间的有效互补并防止噪声干扰,我们首先在特征增强模块(FEB)中平等对待 RGB 和热图像,并进一步,Global Context Module扩展感受野以获得全局特征,Top-Feature Enhancement Module从顶层抑制可能破坏原始特征的冗余信息。随后,我们将几个交叉特征聚合模块(CFAM)嵌入到聚合和反馈解码器中,以融合不同级别的特征和补偿特征,以进一步获得全面的特征表达。此外,采用反馈机制将这些融合特征传播回之前的层进行细化,并生成显着性图以渐进方式解码特征。对 RGB-T 数据集的综合实验表明,EAF-Net 与最先进的模型相比具有出色的性能。我们将几个交叉特征聚合模块(CFAM)嵌入到聚合和反馈解码器中,以融合不同级别的特征和补偿特征,以进一步获得全面的特征表达。此外,采用反馈机制将这些融合特征传播回之前的层进行细化,并生成显着性图以渐进方式解码特征。对 RGB-T 数据集的综合实验表明,EAF-Net 与最先进的模型相比具有出色的性能。我们将几个交叉特征聚合模块(CFAM)嵌入到聚合和反馈解码器中,以融合不同级别的特征和补偿特征,以进一步获得全面的特征表达。此外,采用反馈机制将这些融合特征传播回之前的层进行细化,并生成显着性图以渐进方式解码特征。对 RGB-T 数据集的综合实验表明,EAF-Net 与最先进的模型相比具有出色的性能。采用反馈机制将这些融合特征传播回之前的层进行细化,并生成显着性图以渐进方式解码特征。对 RGB-T 数据集的综合实验表明,EAF-Net 与最先进的模型相比具有出色的性能。采用反馈机制将这些融合特征传播回之前的层进行细化,并生成显着性图以渐进方式解码特征。对 RGB-T 数据集的综合实验表明,EAF-Net 与最先进的模型相比具有出色的性能。

更新日期:2022-07-14
down
wechat
bug