ASF-YOLO: A novel YOLO model with attentional scale sequence fusion for cell instance segmentation

Kang, Ming; Ting, Chee-Ming; Ting, Fung Fung; Phan, Raphaël C.-W.

doi:10.1016/j.imavis.2024.105057

Cited by 31 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, various feature pyramid network structures fail to effectively exploit the correlation among all pyramid feature maps, which may lead to a decrease in model accuracy. The SSFF [27] module utilizes a novel scale sequence feature fusion method, which can better integrate the high-dimensional information of deep feature maps with the detailed information of shallow feature maps. During the image downsampling process, the size of the image changes, but the scale-invariant features remain unchanged.…”

Section: Ssff Modulementioning

confidence: 99%

A Lightweight Remote Sensing Small Target Image Detection Algorithm Based on Improved YOLOv8

Nie,

Pang,

et al. 2024

Sensors

View full text Add to dashboard Cite

In response to the challenges posed by small objects in remote sensing images, such as low resolution, complex backgrounds, and severe occlusions, this paper proposes a lightweight improved model based on YOLOv8n. During the detection of small objects, the feature fusion part of the YOLOv8n algorithm retrieves relatively fewer features of small objects from the backbone network compared to large objects, resulting in low detection accuracy for small objects. To address this issue, firstly, this paper adds a dedicated small object detection layer in the feature fusion network to better integrate the features of small objects into the feature fusion part of the model. Secondly, the SSFF module is introduced to facilitate multi-scale feature fusion, enabling the model to capture more gradient paths and further improve accuracy while reducing model parameters. Finally, the HPANet structure is proposed, replacing the Path Aggregation Network with HPANet. Compared to the original YOLOv8n algorithm, the recognition accuracy of mAP@0.5 on the VisDrone data set and the AI-TOD data set has increased by 14.3% and 17.9%, respectively, while the recognition accuracy of mAP@0.5:0.95 has increased by 17.1% and 19.8%, respectively. The proposed method reduces the parameter count by 33% and the model size by 31.7% compared to the original model. Experimental results demonstrate that the proposed method can quickly and accurately identify small objects in complex backgrounds.

show abstract

Section: Ssff Modulementioning

confidence: 99%

A Lightweight Remote Sensing Small Target Image Detection Algorithm Based on Improved YOLOv8

Nie,

Pang,

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…The resulting AIFI-HiLo module captures both local details and global dependencies in feature maps. Subsequently, the proposed slimneck-SSFF structure for feature fusion, which combines a scaled sequence feature fusion framework [33] with a slim neck design, employs GSConv and VoVGSCSP modules [34] to reduce computational costs and inference latency, enhancing the focus on small target features. Finally, Inner-IoU [35] is combined with GIoU [36] to form Inner-GIoU, using a scale factor ratio to control the auxiliary bounding box size for loss computation in order to accelerate convergence and improve the detection of extremely small targets.…”

Section: The Phsi-rtdetr Model Architecturementioning

confidence: 99%

PHSI-RTDETR: A Lightweight Infrared Small Target Detection Algorithm Based on UAV Aerial Photography

Wang,

Jiang,

et al. 2024

Drones

View full text Add to dashboard Cite

To address the issues of low model accuracy caused by complex ground environments and uneven target scales and high computational complexity in unmanned aerial vehicle (UAV) aerial infrared image target detection, this study proposes a lightweight UAV aerial infrared small target detection algorithm called PHSI-RTDETR. Initially, an improved backbone feature extraction network is designed using the lightweight RPConv-Block module proposed in this paper, which effectively captures small target features, significantly reducing the model complexity and computational burden while improving accuracy. Subsequently, the HiLo attention mechanism is combined with an intra-scale feature interaction module to form an AIFI-HiLo module, which is integrated into a hybrid encoder to enhance the focus of the model on dense targets, reducing the rates of missed and false detections. Moreover, the slimneck-SSFF architecture is introduced as the cross-scale feature fusion architecture of the model, utilizing GSConv and VoVGSCSP modules to enhance adaptability to infrared targets of various scales, producing more semantic information while reducing network computations. Finally, the original GIoU loss is replaced with the Inner-GIoU loss, which uses a scaling factor to control auxiliary bounding boxes to speed up convergence and improve detection accuracy for small targets. The experimental results show that, compared to RT-DETR, PHSI-RTDETR reduces model parameters by 30.55% and floating-point operations by 17.10%. Moreover, detection precision and speed are increased by 3.81% and 13.39%, respectively, and mAP50, impressively, reaches 82.58%, demonstrating the great potential of this model for drone infrared small target detection.

show abstract

“…The enhancement of the Head component is attained through the implementation of Attentional Scale Sequence Fusion (ASF) in ASF-YOLO, along with the integration of the P2 detection layer and optimization of the network architecture. ASF-YOLO (depicted in Figure 4 ) represents a novel YOLO framework introduced by Ming Kang [ 25 ], amalgamating spatial and scale features to achieve precise and rapid cell instance segmentation. This framework extends the Yolo segmentation model, incorporating the Scale Sequence Feature Fusion (SSFF) module to bolster the network’s multi-scale information extraction capacity and the Triple Feature Encoder (TFE) module to fuse feature maps across various scales for detailed information augmentation.…”

Section: Yolov8n-fads Detection Modelmentioning

confidence: 99%

Yolov8n-FADS: A Study for Enhancing Miners’ Helmet Detection Accuracy in Complex Underground Environments

Fu,

Ling,

Yuan

et al. 2024

Sensors

View full text Add to dashboard Cite

A new algorithm, Yolov8n-FADS, has been proposed with the aim of improving the accuracy of miners’ helmet detection algorithms in complex underground environments. By replacing the head part with Attentional Sequence Fusion (ASF) and introducing the P2 detection layer, the ASF-P2 structure is able to comprehensively extract the global and local feature information of the image, and the improvement in the backbone part is able to capture the spatially sparsely distributed features more efficiently, which improves the model’s ability to perceive complex patterns. The improved detection head, SEAMHead by the SEAM module, can handle occlusion more effectively. The Focal Loss module can improve the model’s ability to detect rare target categories by adjusting the weights of positive and negative samples. This study shows that compared with the original model, the improved model has 29% memory compression, a 36.7% reduction in the amount of parameters, and a 4.9% improvement in the detection accuracy, which can effectively improve the detection accuracy of underground helmet wearers, reduce the workload of underground video surveillance personnel, and improve the monitoring efficiency.

show abstract

ASF-YOLO: A novel YOLO model with attentional scale sequence fusion for cell instance segmentation

Cited by 31 publications

References 20 publications

A Lightweight Remote Sensing Small Target Image Detection Algorithm Based on Improved YOLOv8

A Lightweight Remote Sensing Small Target Image Detection Algorithm Based on Improved YOLOv8

PHSI-RTDETR: A Lightweight Infrared Small Target Detection Algorithm Based on UAV Aerial Photography

Yolov8n-FADS: A Study for Enhancing Miners’ Helmet Detection Accuracy in Complex Underground Environments

Contact Info

Product

Resources

About