SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization

Du, Xianzhi; Lin, Tsung-Yi; Jin, Pengchong; Ghiasi, Golnaz; Tan, Mingxing; Cui, Yin; Le, Quoc V.; Xue, Song

doi:10.1109/cvpr42600.2020.01161

Cited by 166 publications

(119 citation statements)

References 26 publications

Supporting

Mentioning

112

Contrasting

Unclassified

Order By: Relevance

“…Although dissimilar to network pruning, as evidenced in our study, AutoKeras can discover efficient and compact model architectures through the NAS process. However, NAS-generated models are typically limited to variants or combinations of modules derived from existing, human-designed CNN architectures [16,20,21]; although recent innovations in NAS have uncovered novel CNN architectures such as SpineNet for object detection [55].…”

Section: Discussionmentioning

confidence: 99%

Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping

2021

View full text Add to dashboard Cite

Automated machine learning (AutoML) has been heralded as the next wave in artificial intelligence with its promise to deliver high-performance end-to-end machine learning pipelines with minimal effort from the user. However, despite AutoML showing great promise for computer vision tasks, to the best of our knowledge, no study has used AutoML for image-based plant phenotyping. To address this gap in knowledge, we examined the application of AutoML for image-based plant phenotyping using wheat lodging assessment with unmanned aerial vehicle (UAV) imagery as an example. The performance of an open-source AutoML framework, AutoKeras, in image classification and regression tasks was compared to transfer learning using modern convolutional neural network (CNN) architectures. For image classification, which classified plot images as lodged or non-lodged, transfer learning with Xception and DenseNet-201 achieved the best classification accuracy of 93.2%, whereas AutoKeras had a 92.4% accuracy. For image regression, which predicted lodging scores from plot images, transfer learning with DenseNet-201 had the best performance (R2 = 0.8303, root mean-squared error (RMSE) = 9.55, mean absolute error (MAE) = 7.03, mean absolute percentage error (MAPE) = 12.54%), followed closely by AutoKeras (R2 = 0.8273, RMSE = 10.65, MAE = 8.24, MAPE = 13.87%). In both tasks, AutoKeras models had up to 40-fold faster inference times compared to the pretrained CNNs. AutoML has significant potential to enhance plant phenotyping capabilities applicable in crop breeding and precision agriculture.

show abstract

Section: Discussionmentioning

confidence: 99%

Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping

2021

View full text Add to dashboard Cite

show abstract

“…However, NAS generated models are typically limited to variants or combinations of modules derived from existing human designed CNN architectures (Elsken et al, 2019; X. He et al, 2019; Wistuba et al, 2019); although recent innovations in NAS have uncovered novel CNN architectures such as SpineNet for object detection (Du et al, 2019).…”

Section: Discussionmentioning

confidence: 99%

Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping

Koh

Spangenberg

Kant

2020

Preprint

View full text Add to dashboard Cite

Automated machine learning (AutoML) has been heralded as the next wave in artificial intelligence with its promise to deliver high performance end-to-end machine learning pipelines with minimal effort from the user. AutoML with neural architecture search which searches for the best neural network architectures in deep learning has delivered state-of-the-art performance in computer vision tasks such as image classification and object detection. Using wheat lodging assessment with UAV imagery as an example, we compared the performance of an open-source AutoML framework, AutoKeras in image classification and regression tasks to transfer learning using modern convolutional neural network (CNN) architectures pretrained on the ImageNet dataset. For image classification, transfer learning with Xception and DenseNet-201 achieved best classification accuracy of 93.2%, whereas Autokeras had 92.4% accuracy. For image regression, transfer learning with DenseNet-201 had the best performance (R2=0.8303, RMSE=9.55, MAE=7.03, MAPE=12.54%), followed closely by AutoKeras (R2=0.8273, RMSE=10.65, MAE=8.24, MAPE=13.87%). Interestingly, in both tasks, AutoKeras generated compact CNN models with up to 40-fold faster inference times compared to the pretrained CNNs. The merits and drawbacks of AutoML compared to transfer learning for image-based plant phenotyping are discussed.

show abstract

“…To verify the effectiveness of MaskHunter proposed, we compare MaskHunter with other state‐of‐the‐art object detectors in the practical application of face mask real‐time detection. The other object detectors for comparison include faster R‐CNN [17], SSD [20], YOLOv3 [52], original YOLOv4 [12], YOLOv4‐large [53], EfficientDet D3‐D5 [41], Mask R‐CNN [46], EFGRNet [54] and SpineNet [55].…”

Section: Methodsmentioning

confidence: 99%

MaskHunter: real‐time object detection of face masks during the COVID‐19 pandemic

Cao

Shao

et al. 2020

IET image process

View full text Add to dashboard Cite

Due to the COVID-19 pandemic at present, it is necessary to detect whether pedestrians in public places wear face masks or not for preventing the spread of novel coronavirus. The pedestrian flow in public places is large, and it puts forward higher requirements for the accuracy and speed of real-time mask detection. Improving the face mask detection effect especially in the night environment is a challenging problem. A novel object detector namely MaskHunter is proposed in this study for the real-time mask detection. Specifically, the authors propose novel effective structures of backbone, neck and prediction head based on YOLOv4 series, which achieves the state-of-the-art performance and a novel improved Mosaic data augmentation method. Moreover, they propose a novel mask-guided module to enhance the discrimination ability of face mask especially in the night environment. As a consequent, experiments show that MaskHunter achieves better detection performance for realtime mask detection compared with other obtained models in this scenario.

show abstract

SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization

Cited by 166 publications

References 26 publications

Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping

Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping

Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping

MaskHunter: real‐time object detection of face masks during the COVID‐19 pandemic

Contact Info

Product

Resources

About