Augmented Score-CAM: High resolution visual interpretations for deep neural networks

Ibrahim, Rami; Shafiq, Omair

doi:10.1016/j.knosys.2022.109287

Cited by 20 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a sense, it mixes CAM methods with perturbations methods [10]. Multiple methods expanding this concept are also described such as SS-CAM [17], IS-CAM [18] or Augmented Score-CAM [19]. Ablation-CAM [20] propose to apply the perturbation inside of the network by alternatively switching off each channel at the last convolutional layer and evaluate the change in classification.…”

Section: Related Workmentioning

confidence: 99%

Poly-CAM: High resolution Class Activation Map for Convolutional Neural Networks

Englebert,

Cornu,

De Vleeschouwer

2024

Preprint

View full text Add to dashboard Cite

The demand for explainable AI continues to rise alongside advancements in deep learning technology. Existing methods such as convolutional neural networks often struggle to accurately pinpoint the image features justifying a network's prediction due to low-resolution saliency maps (e.g., CAM), smooth visualizations from perturbation-based techniques, or numerous isolated peaky spots in gradient-based approaches. In response, our work seeks to merge information from earlier and later layers within the network to create high-resolution class activation maps that not only maintain a level of competitiveness with previous art in terms of insertion-deletion faithfulness metrics but also significantly surpass it regarding the precision of localizing class-specific features.

show abstract

Section: Related Workmentioning

confidence: 99%

Poly-CAM: High resolution Class Activation Map for Convolutional Neural Networks

Englebert,

Cornu,

De Vleeschouwer

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…35 An enhanced Score-CAM model has been proposed to provide interpretability to deep learning models, thereby increasing their transparency and explainability. 36 Furthermore, a risk prediction system for online lending platforms has been introduced, leveraging convolutional neural networks and Stacking ensemble models. This system outperforms single models and other ensemble models in terms of prediction accuracy and recall.…”

Section: Deep Learning Modelmentioning

confidence: 99%

“…The system exhibits superior performance compared to the market in metrics such as maximum drawdown, Sharpe ratio, and Sortino ratio 35 . An enhanced Score‐CAM model has been proposed to provide interpretability to deep learning models, thereby increasing their transparency and explainability 36 . Furthermore, a risk prediction system for online lending platforms has been introduced, leveraging convolutional neural networks and Stacking ensemble models.…”

Section: Related Workmentioning

confidence: 99%

Joint loan risk prediction based on deep learning‐optimized stacking model

Wang,

Pan

et al. 2023

Engineering Reports

View full text Add to dashboard Cite

In recent years, China's automobile industry has undergone rapid development, creating new opportunities for the auto loan industry. Currently, auto financing companies are actively seeking to expand their cooperation with banks. Therefore, improving the approval rate and scale of joint loan business is of significant practical importance. In this paper, we propose a Stacking‐based financial institution risk approval model and select the optimal stacking model by comparing its performance with other models. Additionally, we construct a bank approval model using deep learning techniques on a biased data set, with feature extraction performed using convolution neural networks (CNN) and feature‐based counterfactual augmentation used for balanced sampling. Finally, we optimize the model of the prediction of auto finance companies by selecting the optimal coefficients of loss function based on the features and results of the bank approval model. The proposed approach leads to an approximately 6% increase in the joint loan approval rate on the actual data set, as demonstrated by experimental results.

show abstract

“…Deep neural networks have been widely used in many fields, such as computer vision, recommender systems, and semantic segmentation, and have shown good performance [1]. These tasks are mostly based on convolutional neural networks (CNNs) to build decision models, and the trained models have excellent automatic feature extraction and decisionmaking capabilities.…”

Section: Introductionmentioning

confidence: 99%

Augmented Grad-CAM++: Super-Resolution Saliency Maps for Visual Interpretation of Deep Neural Network

Gao,

Liu,

et al. 2023

Electronics

View full text Add to dashboard Cite

In recent years, deep neural networks have shown superior performance in various fields, but interpretability has always been the Achilles’ heel of deep neural networks. The existing visual interpretation methods for deep neural networks still suffer from inaccurate and insufficient target localization and low-resolution saliency maps. To address the above issues, this paper presents a saliency map generation method based on image geometry augmentation and super-resolution called augmented high-order gradient weighting class activation mapping (augmented grad-CAM++). Unlike previous approaches that rely on a single input image to generate saliency maps, this method first introduces the image geometry augmentation technique to create a set of augmented images for the input image and generate activation mappings separately. Secondly, the augmented activation mappings are combined to form the final saliency map. Finally, a super-resolution technique is introduced to add pixel points to reconstruct the saliency map pixels to improve the resolution of the saliency map. The proposed method is applied to analyze standard image data and industrial surface defect images. The results indicate that, in experiments conducted on standard image data, the proposed method achieved a 3.1% improvement in the accuracy of capturing target objects compared to traditional methods. Furthermore, the resolution of saliency maps was three times higher than that of traditional methods. In the application of industrial surface defect detection, the proposed method demonstrated an 11.6% enhancement in the accuracy of capturing target objects, concurrently reducing the false positive rate. The presented approach enables more accurate and comprehensive capture of target objects with higher resolution, thereby enhancing the visual interpretability of deep neural networks. This improvement contributes to the greater interpretability of deep learning models in industrial applications, offering substantial performance gains for the practical deployment of deep learning networks in the industrial domain.

show abstract

Augmented Score-CAM: High resolution visual interpretations for deep neural networks

Cited by 20 publications

References 24 publications

Poly-CAM: High resolution Class Activation Map for Convolutional Neural Networks

Poly-CAM: High resolution Class Activation Map for Convolutional Neural Networks

Joint loan risk prediction based on deep learning‐optimized stacking model

Augmented Grad-CAM++: Super-Resolution Saliency Maps for Visual Interpretation of Deep Neural Network

Contact Info

Product

Resources

About