2020
DOI: 10.1109/access.2020.2982939
|View full text |Cite
|
Sign up to set email alerts
|

GeminiNet: Combine Fully Convolution Network With Structure of Receptive Fields for Object Detection

Abstract: Pneumonia is a relatively common disease that will endanger the lives of patients if left untreated. End-to-end detection of pneumonia using neural networks will be helpful for reducing related workforce. CNN's processing of images shows remarkable performance, naturally, the use of CNN based methods for assisted reading will be a trend in modern medicine. The property of current detection algorithms is not yet satisfactory, so further research is extremely needed. In this article, we design GeminiNet to ident… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 12 publications
(7 citation statements)
references
References 22 publications
0
5
0
Order By: Relevance
“…Keeping this in mind, Yao et al 42 presented the GeminiNet in March 2020. Before we begin with the explanation of this study, there is a note worth taking.…”
Section: Methodsmentioning
confidence: 99%
“…Keeping this in mind, Yao et al 42 presented the GeminiNet in March 2020. Before we begin with the explanation of this study, there is a note worth taking.…”
Section: Methodsmentioning
confidence: 99%
“…We perform quantitative comparisons with recent state-ofthe-art methods [14], [24], [33], [43] on the RSNA dataset.…”
Section: ) Abnormality Detectionmentioning
confidence: 99%
“…Method AP AP 0.4 AP 0.5 AP 0.6 Faster RCNN [44] 0.430 0.586 0.438 0.266 SSD [45] 0.404 0.559 0.406 0.247 Yolo_v3 [46] 0.434 0.579 0.430 0.292 PYolo_v3 [33] 0.468 0.642 0.447 0.316 Mask RCNN [38] +align 0.476 0.645 0.504 0.279 Mask RCNN [38] +align, residual 0.520 0.695 0.554 0.311 A comparative evaluation of GeminiNet [43], the modified RetinaNet † [14], the disentangled generative model (DGM) [24], and the proposed method based on RetinaNet † is presented in Table 1, with the experimental setting following [14]. The evaluation of Faster RCNN [44], SSD [45], YOLO [46], PYolo [33], and the proposed method based on Mask-RCNN [38] is presented in Table 2, with the experimental setting following [33].…”
Section: ) Abnormality Detectionmentioning
confidence: 99%
See 1 more Smart Citation
“…The feature extraction network uses the improved DetNet59 [4], [9], [31], [33] as the backbone network, which combines the spatial pyramid structure (FPN) number of channels of the output feature map of each layer of the network is fixed at 256. Then, the feature map output of different layers is fused by using the feature pyramid network [16], [26], [8],…”
Section: Feature Extractionmentioning
confidence: 99%