2021
DOI: 10.1016/j.ins.2020.09.058
|View full text |Cite
|
Sign up to set email alerts
|

Analysis of activation maps through global pooling measurements for texture classification

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
17
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
5
1
1

Relationship

1
6

Authors

Journals

citations
Cited by 12 publications
(17 citation statements)
references
References 24 publications
0
17
0
Order By: Relevance
“…The A (l) measurements then become the inputs to an FC layer. In [20], these pooling measurements were transformed into feature vectors. Two global pooling measurements are used for feature extraction in the experiments presented here: global entropy pooling (GEP) and global mean thresholding pooling (GMTP).…”
Section: Global Pooling Measurementsmentioning
confidence: 99%
See 1 more Smart Citation
“…The A (l) measurements then become the inputs to an FC layer. In [20], these pooling measurements were transformed into feature vectors. Two global pooling measurements are used for feature extraction in the experiments presented here: global entropy pooling (GEP) and global mean thresholding pooling (GMTP).…”
Section: Global Pooling Measurementsmentioning
confidence: 99%
“…In [19], features were extracted from the penultimate layers of pretrained CNNs and merged with the outputs of the deep layers and CNN scores. Finally, in [20], features were investigated layer by layer and were discovered to provide quality information about the texture of images at multiple depths.…”
Section: Introductionmentioning
confidence: 99%
“…Additionally, we used PyTorch 1.0 (PASZKE et al, 2017) to import the pre-trained weights for BN-VGG-19 and INCEPTION-V3, and we used Keras (CHOLLET et al, 2015) to import the pre-trained weights for RESNET-50. Source: Adapted from M. Condori and Bruno (2021).…”
Section: Target Task Datasets and Pre-trained Modelsmentioning
confidence: 99%
“…Indeed, Cui et al (2018) have shown that measuring the similarity between the source domain and the target domain is crucial for fine-tuning TL methods since it could determine beforehand whether good results are possible in the target domain. Source: Adapted from M. Condori and Bruno (2021).…”
Section: Performance Of Gap Features Across Multiple Depth Levelsmentioning
confidence: 99%
See 1 more Smart Citation