Visualizing Feature Maps for Model Selection in Convolutional Neural Networks

Mostafa, Sakib; Mondal, Debajyoti; Beck, Michael A.; Bidinosti, Christopher; Henry, Christopher J.; Stavness, Ian

doi:10.1109/iccvw54120.2021.00157

Cited by 9 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Secondly, we find that the correlation scores of the last stage are larger than previous stages. This phenomenon is consistent with findings in previous work [75], namely that the features learned in the shallow layers are more diverse than the features learned in the deeper layers. These results demonstrate that our proposed method could significantly reduce redundancy in features and learn more diverse feature representation.…”

Section: Gca Module Effect Analysissupporting

confidence: 93%

GCA: A Graph-based Channel Attention Module for Convolutional Neural Networks

Chang¹

2023

Preprint

View full text Add to dashboard Cite

show abstract

Section: Gca Module Effect Analysissupporting

confidence: 93%

GCA: A Graph-based Channel Attention Module for Convolutional Neural Networks

Chang¹

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…2. Visualization of the feature maps helps to understand the internal representation of the convolutional layers in a CNN model [84]. The feature maps of convolutional layers provide insights into the learning and functioning of the layer [85].…”

Section: Discussionmentioning

confidence: 99%

Gabor CNN Based Intelligent System for Visual Sentiment Analysis of Social Media Data on Cloud Environment

2022

View full text Add to dashboard Cite

Social media contains a plethora of information in the form of text, images, videos, and other data. Users across the globe are increasingly sharing their data on various social media platforms. Sentiment analysis of data, such as text, images, and videos are widely used to understand the feelings of users. In recent years, the convolutional neural network (CNN) has been extensively applied for various applications. The cloud computing environment is a popular service due to its reliability, availability, and easy software integration. However, CNN models are deep neural networks that have a high computational cost. There is a need for CNN models which utilize lesser computational resources especially when these models are deployed in a cloud environment due to the remote physicality of servers, resource optimization, and infrastructure cost reduction. In this research, Gabor filters are integrated with CNN models to improve image sentiment analysis in a cloud environment, with advantages such as the reduction in computation energy and time, the elimination of the need for pre-trained models, and a perceived accuracy improvement. Two variants of Gabor-CNN (G-CNN) models with a different number of pooling and normalization layers are developed. The proposed G-CNN is trained and tested using five standard databases as SentiBank, Twitter, MVSO, MultiView_I, and MultiView_II. Maximum classification accuracies of 91.71%, 92.52%, 97.39%, 90.88%, and 91.31% are obtained on SentiBank, Twitter, MVSO, MultiView_I, and MultiView_II databases respectively using the developed models. The proposed G-CNN model has provided an accuracy of 92.76% on average.

show abstract

“…For all the datasets, 80% of the available images were used for training and 10% for testing and 10% for validation. The detailed overview of the datasets is available in Mostafa et al ( 2021 ).…”

Section: Methodsmentioning

confidence: 99%

“…The content of this manuscript has been presented [IN PART] at the Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, 1362-1371 (Mostafa et al, 2021 ).…”

mentioning

confidence: 99%

Leveraging Guided Backpropagation to Select Convolutional Neural Networks for Plant Classification

Mostafa

Mondal

Beck

et al. 2022

Front. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

The development of state-of-the-art convolutional neural networks (CNN) has allowed researchers to perform plant classification tasks previously thought impossible and rely on human judgment. Researchers often develop complex CNN models to achieve better performances, introducing over-parameterization and forcing the model to overfit on a training dataset. The most popular process for evaluating overfitting in a deep learning model is using accuracy and loss curves. Train and loss curves may help understand the performance of a model but do not provide guidance on how the model could be modified to attain better performance. In this article, we analyzed the relation between the features learned by a model and its capacity and showed that a model with higher representational capacity might learn many subtle features that may negatively affect its performance. Next, we showed that the shallow layers of a deep learning model learn more diverse features than the ones learned by the deeper layers. Finally, we propose SSIM cut curve, a new way to select the depth of a CNN model by using the pairwise similarity matrix between the visualization of the features learned at different depths by using Guided Backpropagation. We showed that our proposed method could potentially pave a new way to select a better CNN model.

show abstract

Visualizing Feature Maps for Model Selection in Convolutional Neural Networks

Cited by 9 publications

References 30 publications

GCA: A Graph-based Channel Attention Module for Convolutional Neural Networks

GCA: A Graph-based Channel Attention Module for Convolutional Neural Networks

Gabor CNN Based Intelligent System for Visual Sentiment Analysis of Social Media Data on Cloud Environment

Leveraging Guided Backpropagation to Select Convolutional Neural Networks for Plant Classification

Contact Info

Product

Resources

About