Grad-CAM based visualization of 3D CNNs in classifying fMRI

Fu, Jiajun; Lu, Meili; Cao, Yifan; Guo, Zherui; Gao, Zicheng

doi:10.1117/12.2643867

Cited by 16 publications

(31 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GradCAM [47] and GradCAM++ [48] use the layer's gradient to compute coefficients. XGrad-CAM [49] proposes the use of axioms to avoid the use of heuristic methods. LIFT-CAM [50] proposes an analytical solution to the problem.…”

Section: Activation Maximisation (Am)mentioning

confidence: 99%

Hypericons for Abstract Concepts: Non-traditional Approaches to Visual Explainability

Pandiani

Lazzari

Erp

et al. 2023

Preprint

View full text Add to dashboard Cite

In the cultural heritage (CH) field, abstract concepts–such as comfort, power, or freedom–are considered powerful tools to index cultural visual data. Simultaneously, the ever-increasing number of images is too great to index manually, so computer vision (CV)-based methods are employed to automatically classify images. The CV field, however, has paid scarce attention to image classification based on abstract concepts, partly because it has historically favored tasks and datasets for purportedly objective, concrete categories. More subjective and culturally-coded classes, like abstract concepts, more explicitly require interpretability of predictions by automatic models, given the potential to echo harmful bias. This is especially true for their detection in CH collections, given that they tend to contain many `ethically sensitive' depictions. To address the gap in CV-based interpretable methods for automatic classification of abstract concepts, we (1) present ARTstract, a dataset of cultural images and their evocation of certain abstract concepts (2) report baseline model performances on ARTstract for the task of image classification by abstract concepts, and, critically, (3) use them as a case study of traditional and non-traditional approaches to visual interpretability, inspired by [Offert \& Bell 2021]’s work. We introduce a unique approach to testing the interpretability of predictions by automatic models, using a combination of attribution maps (AM) and stable diffusion (SD). This approach has not been attempted before, and we experiment with it as a way to extend hermeneutic work back into the technical system that enables, unveiling its potential as a provider of lessons for developing systems that are interpretable-by-design.

show abstract

Section: Activation Maximisation (Am)mentioning

confidence: 99%

Hypericons for Abstract Concepts: Non-traditional Approaches to Visual Explainability

Pandiani

Lazzari

Erp

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Other authors introduce important properties that an explanation should possess, such as consistency and local fidelity, 9 sensitivity and conservation, 14 or sensitivity and invariance to implementation. 18 Similarly, the fidelity of saliency maps has been assessed using dedicated objective metrics, 10,[12][13][14]55 which are called interchangeably fidelity, reliability, or faithfulness metrics. These metrics consist in perturbing the image processed by the model to determine whether the areas emphasized by the explanation contribute significantly to the class score.…”

Section: Objective Evaluationmentioning

confidence: 99%

Computing and evaluating saliency maps for image classification: a tutorial

Gomez

Mouchère

2023

J. Electron. Imag.

View full text Add to dashboard Cite

Facing the black-box nature of deep learning models for image classification, a popular trend in the literature proposes methods to generate explanations in the form of heat maps indicating the areas that played an important role in the models' decisions. Such explanations are called saliency maps and constitute an active field of research, given that many fundamental questions are yet to be answered: how to compute them efficiently? How to evaluate them? What exactly can they be used for? Given the increasing rate at which papers are produced and the vast amount of literature that is already existing, we propose our study to help newcomers become part of this community and to contribute to the research field. First, the two existing approaches to generate saliency maps are discussed, namely post-hoc methods and attention models. Post-hoc methods are generic algorithms that can be applied to any model from a given class without requiring fine-tuning. On the contrary, attention models are ad-hoc architectures that generate a saliency map during the inference phase to guide the decision. We show that both approaches can be divided into several subcategories and illustrate each of them with one important model or method. Second, we present the current methodologies used to evaluate saliency maps, including objective and subjective protocols, depending on whether or not they involve users. Among objective methods, we notably detail faithfulness metrics and propose an implementation featuring the faithfulness metrics discussed in this paper (https://github. com/TristanGomez44/metrics-saliency-maps).

show abstract

“…In this section, we first review the existing classical methods of CAM [31][32][33][34][35][36][37] and the 129…”

Section: Related Workmentioning

confidence: 99%

C-RISE: A Post-hoc Interpretation Method of Black-box Models for SAR ATR

Zhu¹,

Cheng²,

Lei³

et al. 2023

Preprint

View full text Add to dashboard Cite

The integration of deep learning methods, especially Convolutional Neural Networks (CNN), and Synthetic Aperture Radar Automatic Target Recognition (SAR ATR) has been widely deployed in the field of radar signal processing. Nevertheless, these methods are frequently regarded as black-box models due to the limited visual interpretation of their internal feature representation and parameter organization. In this paper, we propose an innovative approach named C-RISE, which builds upon the RISE algorithm to provide a post-hoc interpretation technique for black-box models used in SAR Images Target Recognition. C-RISE generates saliency maps that effectively visualize the significance of each pixel. Our algorithm outperforms RISE by clustering masks that capture similar fusion features into distinct groups, enabling more appropriate weight distribution and increased focus on the target area. Furthermore, we employ Gaussian blur to process the masked area, preserving the original image structure with optimal consistency and integrity. C-RISE has been extensively evaluated through experiments, and the results demonstrate superior performance over other interpretation methods based on perturbation when applied to neural networks for SAR image target recognition. Furthermore, our approach is highly robust and transferable compared to other interpretable algorithms, including white-box methods.

show abstract

Grad-CAM based visualization of 3D CNNs in classifying fMRI

Cited by 16 publications

References 14 publications

Hypericons for Abstract Concepts: Non-traditional Approaches to Visual Explainability

Hypericons for Abstract Concepts: Non-traditional Approaches to Visual Explainability

Computing and evaluating saliency maps for image classification: a tutorial

C-RISE: A Post-hoc Interpretation Method of Black-box Models for SAR ATR

Contact Info

Product

Resources

About