A lightweight network for smoke semantic segmentation. (May 2023)

• Record Type: Journal Article
• Authors: Yuan, Feiniu; Li, Kang; Wang, Chunmei; Fang, Zhijun
• Is Part Of: Pattern recognition. Volume 137(2023)
• Publication Date: 2023-05
• Subjects: Smoke semantic segmentation -- Deep learning -- Attention mechanism -- Lightweight network -- Channel split and shuffle; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.109289
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We propose an attention encoding module (AEM) to enhance the ability of feature encoding. We propose a spatial enhancement module (SEM) and a channel attention module (CAM) to improve robustness of encoding features with different levels. We propose a feature fusion module (FFM) and a global coefficient path (GCP) to fuse the features of SEM and CAM. We propose a lightweight network with less than 1 M parameters for smoke segmentation. Abstract: To obtain real-time performance on computation limited devices, we propose a lightweight network for smoke segmentation. To enhance the ability of feature encoding, we first propose an Attention Encoding Module (AEM) by designing a Channel Split and Shuffle Attention Module (CSSAM), which can extract powerful features and reduce computations simultaneously. CSSAM adopts Channel split and shuffle to greatly reduce learnable parameters for improving computation speed, and uses attention mechanism to focus on salient objects to enhance the effectiveness of features. In addition, AEM repeatedly stacks CSSAM in different encoding stages to achieve scale invariance. For the middle-level features of encoding stages, we propose a Spatial Enhancement Module (SEM) to boost the representation ability of spatial details. SEM concatenates feature maps produced by average and maximum pooling to achieve dominant and global responses, which are then weighted by the activated output of global average pooling to generate attention features. In the highest level of encoding stages, we present a Channel Attention Module (CAM) to explicitly model interdependency between channels. By reshaping 2D features into 1D features, we use element-wise matrix multiplications to reduce computation complexity for extracting channel-related information. Finally, we design a Feature Fusion Module (FFM) and a Global Coefficient Path (GCP) to fuse the outputs of SEM and CAM in an attention way for further improving robustness of final features. Experiments show that our method is significantly superior to existing state-of-the-art algorithms in smoke datasets, and also obtains excellent results in both synthetic and real smoke datasets. However, our method has less than 1 M network parameters.