Cross-Iteration Batch Normalization

Yao, Zhuliang; Cao, Yue; Zheng, Shuxin; Huang, Gao; Lin, Stephen

doi:10.1109/cvpr46437.2021.01215

Cited by 64 publications

(16 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…YOLO v4 [48] has put to the test a large variety of strategies that are supposed to enhance accuracy of a CNN. Finally, it combines techniques such as Weighted-Residual-Connections [30], Cross-Stage-Partial-Connections [49], Cross mini-Batch Normalization [50], Self-adversarial-training [51], Mish activation [52], Mosaic data augmentation, DropBlock regularization [53], and CIoU loss [54] to achieve optimal object detection speed and accuracy. In [55], to construct a lightweight underwater object detector, YOLO v4 is combined with a multi-scale attentional feature fusion module.…”

Section: One-stage Detectorsmentioning

confidence: 99%

Marine Robotics 4.0: Present and Future of Real-Time Detection Techniques for Underwater Objects

Er¹,

Chen²,

Zhang³

2023

Artificial Intelligence

View full text Add to dashboard Cite

Underwater marine robots (UMRs), such as autonomous underwater vehicles, are promising alternatives for mankind to perform exploration tasks in the sea. These vehicles have the capability of exploring the underwater environment with onboard instruments and sensors. They are extensively used in civilian applications, scientific studies, and military missions. In recent years, the flourishing growth of deep learning has fueled tremendous theoretical breakthroughs and practical applications of computer-vision-based underwater object detection techniques. With the integration of deep-learning-based underwater object detection capability on board, the perception of underwater marine robots is expected to be enhanced greatly. Underwater object detection will play a key role in Marine Robotics 4.0, i.e., Industry 4.0 for Marine Robots. In this chapter, one of the key research challenges, i.e., real-time detection of underwater objects, which has prevented many real-world applications of object detection techniques onboard UMRs, is reviewed. In this context, state-of-the-art techniques for real-time detection of underwater objects are critically analyzed. Futuristic trends in real-time detection techniques of underwater objects are also discussed.

show abstract

Section: One-stage Detectorsmentioning

confidence: 99%

Marine Robotics 4.0: Present and Future of Real-Time Detection Techniques for Underwater Objects

Er¹,

Chen²,

Zhang³

2023

Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…CSP implementation reduces compute by as much as 20% and outperforms other state-of-the-art backbone architectures [8]. c. Cross Mini-Batch Normalization overcomes the problem where the statistics generated when normalization is defined cannot be estimated properly [9]. d. Self-adversarial Training is a new data augmentation technique that operates in 2 stages forward and backward on the network [10].…”

Section: You Only Look Once (Yolo)mentioning

confidence: 99%

Comparison of CSPDarkNet53, CSPResNeXt-50, and EfficientNet-B0 Backbones on YOLO V4 as Object Detector

Mahasin

Dewi

2022

Int. J. Eng. Scie. and Inform. Technology.

View full text Add to dashboard Cite

YOLO v4 has a structure consisting of 3 parts: backbone, neck, and head. The backbone is a part of the YOLO v4 structure that serves as a feature extractor from the image; the backbone is also a convolutional neural network that can be replaced with another convolutional neural network. Many backbones are recommended by previous research, such as CSPDarkNet53, CSPResNeXt-50, and EfficientNet-B0. Therefore, research needs to be done to determine the effect of different backbones on the YOLO v4 model. One of the research objects that can be used is a microfossil. Research on the detection of microfossils is fundamental to assist paleontologists in knowing the species of microfossils as a determinant of rock age and distinguishing between similar microfossils. In this research, three backbones consisting of CSPDarkNet53, CSPResNeXt-50, and EfficientNet-B0 were used to train and detect image sets of 5 species of foraminiferal microfossils. The results were evaluated to determine the advantages of each backbone. There are a few metrics are that being used for evaluation, namely precision, recall, f1-score, average precision (AP), mean average precision (mAP), frames per second (FPS), and model size. As a result, the mean average precision (mAP) of the CSPDarkNet53 model reached 83.41%, the highest compared to CSPResNeXt-50 and EfficientNet-B0, which get a value of 81,00% and 81,76%. CSPResNeXt-50 model has a precision of 75.60%, recall of 81.10%, and f1-score of 78%. CSPDarkNet53 model also got the highest FPS value of 33.4FPS. However, the YOLO v4 model with the EfficientNet-B0 backbone is the lightest model, with only 156.8 MB.

show abstract

“…Bochkovskiy et al also a classified bag of specials as a plugin module and post-processing method that only increases the inference cost by a small amount but can significantly improve accuracy; this includes enlarging the receptive field, an attention module, feature integration, and post-processing. Within the bag of freebies and bag of specials that were evaluated, Bochkovskiy et al introduced 4 modifications: SPP [19], a Spatial Attention Module (SAM) [23], PAN [20], and cross-iteration batch normalization (CBN) [24].…”

Section: Mosquito Surveillance Algorithmmentioning

confidence: 99%

AI-Enabled Mosquito Surveillance and Population Mapping Using Dragonfly Robot

Semwal

Melvin

Elara

et al. 2022

Sensors

View full text Add to dashboard Cite

Mosquito-borne diseases can pose serious risks to human health. Therefore, mosquito surveillance and control programs are essential for the wellbeing of the community. Further, human-assisted mosquito surveillance and population mapping methods are time-consuming, labor-intensive, and require skilled manpower. This work presents an AI-enabled mosquito surveillance and population mapping framework using our in-house-developed robot, named ‘Dragonfly’, which uses the You Only Look Once (YOLO) V4 Deep Neural Network (DNN) algorithm and a two-dimensional (2D) environment map generated by the robot. The Dragonfly robot was designed with a differential drive mechanism and a mosquito trapping module to attract mosquitoes in the environment. The YOLO V4 was trained with three mosquito classes, namely Aedes aegypti, Aedes albopictus, and Culex, to detect and classify the mosquito breeds from the mosquito glue trap. The efficiency of the mosquito surveillance framework was determined in terms of mosquito classification accuracy and detection confidence level on offline and real-time field tests in a garden, drain perimeter area, and covered car parking area. The experimental results show that the trained YOLO V4 DNN model detects and classifies the mosquito classes with an 88% confidence level on offline mosquito test image datasets and scores an average of an 82% confidence level on the real-time field trial. Further, to generate the mosquito population map, the detection results are fused in the robot’s 2D map, which will help to understand mosquito population dynamics and species distribution.

show abstract

Cross-Iteration Batch Normalization

Cited by 64 publications

References 24 publications

Marine Robotics 4.0: Present and Future of Real-Time Detection Techniques for Underwater Objects

Marine Robotics 4.0: Present and Future of Real-Time Detection Techniques for Underwater Objects

Comparison of CSPDarkNet53, CSPResNeXt-50, and EfficientNet-B0 Backbones on YOLO V4 as Object Detector

AI-Enabled Mosquito Surveillance and Population Mapping Using Dragonfly Robot

Contact Info

Product

Resources

About