ETAM: Ensemble transformer with attention modules for detection of small objects

Zhang, Jiangnan; Xia, Kewen; Huang, Zhiyi; Wang, Sijie; Akindele, Romoke Grace

doi:10.1016/j.eswa.2023.119997

Cited by 12 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to IoU, it also considers aspect ratio and centre distance. ETAM (Zhang, Xia, et al, 2023) strives to extract the subtle features of small objects without sacrificing the ability to detect larger objects. A Magnifying Glass (MG) module and Quadruple Attention (QA) are used to focus on the representative features of small objects and to enrich the features of small objects with width and height outside the channel and position, respectively.…”

Section: Related Workmentioning

confidence: 99%

A military reconnaissance network for small‐scale open‐scene camouflaged people detection

Liu

2023

Expert Systems

View full text Add to dashboard Cite

Although the work of identifying animal and plant objects with highly similar patterns (e.g., texture, intensity, colour, etc.) to the background has recently attracted more research interest but rarely involves the military complex environment. Design an efficient camouflage small‐scale object detection algorithm that is capable of quickly discriminating the objects in open scenes from a long distance, to pre‐empt the enemy. In this work, we first recognize the fact that existing open‐source training datasets are scarce, and we have created a specific disguised people benchmark covering multiple scenes and weather conditions. Second, because the severe corruption of camouflage capabilities and chaotic scenes in the open battlefield on detailed features and generalization intensifies the challenge of feature extraction from a long‐range perspective, we propose a novel end‐to‐end Small‐scale open scene Camouflage Object Detection Network, called SM‐CODN. Inspired by the characteristics of biological brain partition, a multi‐domain partition module (MPM) with domain‐decoupling is proposed to enable specific knowledge learning for samples with obvious discrepancies in camouflage domain distribution. Concurrent with our work, we have designed a multi‐scale fusion module (MFM) to strengthen the semantic features related to small‐scale disguised objects. Moreover, due to the convergence direction of the detector in reasoning being inconsistent, a feature separation enhancement module (FSEM) is also proposed. Experimental results show that SM‐CODN surpasses many classic object detection methods and shows strong competitiveness compared with state‐of‐the‐art ones.

show abstract

Section: Related Workmentioning

confidence: 99%

A military reconnaissance network for small‐scale open‐scene camouflaged people detection

Liu

2023

Expert Systems

View full text Add to dashboard Cite

show abstract

“…Zhang et al. [35] present the ensemble transformer with attention modules (ETAM) encoder, a powerful approach for detecting small objects by extracting subtle features. This method leads to significant improvements in small object detection performance across multiple datasets.…”

Section: Related Workmentioning

confidence: 99%

Small object detection based on hierarchical attention mechanism and multi‐scale separable detection

Zhang,

Yu,

Wang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

The ability of modern detectors to detect small targets is still an unresolved topic compared to their capability of detecting medium and large targets in the field of object detection. Accurately detecting and identifying small objects in the real‐world scenario suffer from sub‐optimal performance due to various factors such as small target size, complex background, variability in illumination, occlusions, and target distortion. Here, a small object detection method for complex traffic scenarios named deformable local and global attention (DLGADet) is proposed, which seamlessly merges the ability of hierarchical attention mechanisms (HAMs) with the versatility of deformable multi‐scale feature fusion, effectively improving recognition and detection performance. First, DLGADet introduces the combination of multi‐scale separable detection and multi‐scale feature fusion mechanism to obtain richer contextual information for feature fusion while solving the misalignment problem of classification and localisation tasks. Second, a deformation feature extraction module (DFEM) is designed to address the deformation of objects. Finally, a HAM combining global and local attention mechanisms is designed to obtain discriminative features from complex backgrounds. Extensive experiments on three datasets demonstrate the effectiveness of the proposed methods. Code is available at https://github.com/ACAMPUS/DLGADet

show abstract

“…Thirdly, the maxpooling operation in the SPP module can cause significant information loss, which makes it difficult to obtain local and global information for localization and also results in a significant loss of computation. Fourthly, the information paths connecting different components in the YOLOv5 architecture limit its computational efficiency and are not optimal for feature extraction of small-scale objects [21,22].…”

Section: Yolov5 Basic Network Structurementioning

confidence: 99%

Lightweight PCB defect detection algorithm based on MSD-YOLO

zhou,

Yu,

2023

Preprint

View full text Add to dashboard Cite

Aiming at the problems of low accuracy and slow detection rate of existing target detection algorithms for PCB defect detection, and too many parameters of algorithm model leading to the inability to deploy on mobile terminals, a PCB defect detection algorithm based on MSD-YOLOv5 is proposed.Firstly, to ensure both detection accuracy and speed while reducing the model's size,we combine the lightweight MobileNet-v3 network with the CSPDarknet53 network.Further,the attention mechanism is introduced to highlight the important feature channels and weaken the less useful ones, so as to improve the feature extraction ability of the network. Finally, the coupling detection head is replaced with a decoupling detection head, and the defect location information and category information on the PCB are extracted and learned respectively, which solves the problem of highly coupling of different information feature distributions and enhances the generalization ability of the model.We conduct experiments on a publicly available PCB defect dataset from Peking University using this algorithm.The results show that the proposed method reduces the parameters of YOLOv5 model by 46% and improves the detection accuracy by 3.34%.

show abstract

ETAM: Ensemble transformer with attention modules for detection of small objects

Cited by 12 publications

References 39 publications

A military reconnaissance network for small‐scale open‐scene camouflaged people detection

A military reconnaissance network for small‐scale open‐scene camouflaged people detection

Small object detection based on hierarchical attention mechanism and multi‐scale separable detection

Lightweight PCB defect detection algorithm based on MSD-YOLO

Contact Info

Product

Resources

About