« Previous AbstractPre-compressed polymer cholesteric liquid crystal based optical fiber VOC sensor with high stability and a wide detection range    Next AbstractStrong temperature influence and indiscernible ventilation effect on dynamics of some semivolatile organic compounds in the indoor air of an office »

Sensors (Basel)

Title:		Single-Shot Object Detection via Feature Enhancement and Channel Attention
Author(s):		Li Y; Wang L; Wang Z;
Address:		"College of Mathematics and Computer Science, Zhejiang Normal University, Jinhua 321004, China"
Journal Title:		Sensors (Basel)
Year:		2022
Volume:		20220910
Issue:		18
Page Number:		-
DOI:		10.3390/s22186857
ISSN/ISBN:		1424-8220 (Electronic) 1424-8220 (Linking)
Abstract:		"Features play a critical role in computer vision tasks. Deep learning methods have resulted in significant breakthroughs in the field of object detection, but it is still an extremely challenging obstacle when an object is very small. In this work, we propose a feature-enhancement- and channel-attention-guided single-shot detector called the FCSSD with four modules to improve object detection performance. Specifically, inspired by the structure of atrous convolution, we built an efficient feature-extraction module (EFM) in order to explore contextual information along the spatial dimension, and then pyramidal aggregation module (PAM) is presented to explore the semantic features of deep layers, thus reducing the semantic gap between multi-scale features. Furthermore, we construct an effective feature pyramid refinement fusion (FPRF) to refine the multi-scale features and create benefits for richer object knowledge. Finally, an attention-guided module (AGM) is developed to balance the channel weights and optimize the final integrated features on each level; this alleviates the aliasing effects of the FPN with negligible computational costs. The FCSSD exploits richer information of shallow layers and higher layers by using our designed modules, thus accomplishing excellent detection performance for multi-scale object detection and reaching a better tradeoff between accuracy and inference time. Experiments on PASCAL VOC and MS COCO datasets were conducted to evaluate the performance, showing that our FCSSD achieves competitive detection performance compared with existing mainstream object detection methods"
Keywords:		"Attention *Neural Networks, Computer Records Semantics *Volatile Organic Compounds deep learning feature fusion object detection;"
Notes:		"MedlineLi, Yi Wang, Lingna Wang, Zeji eng 11871438/National Natural Science Foundation of China (NSFC)/ LZ22F020010/Zhejiang Provincial Natural Science Foundation of China/ Switzerland 2022/09/24 Sensors (Basel). 2022 Sep 10; 22(18):6857. doi: 10.3390/s22186857"