Related papers: CNN Explainability with Multivector Tucker Salienc…

Explaining deep convolutional neural networks has been recently drawing increasing attention since it helps to understand the networks' internal operations and why they make certain decisions. Saliency maps, which emphasize salient regions…

Methods based on class activation maps (CAM) provide a simple mechanism to interpret predictions of convolutional neural networks by using linear combinations of feature maps as saliency maps. By contrast, masking-based methods optimize a…

Recent brain tumor classification methods often report high accuracy but rely on deep, over-parameterized architectures with limited interpretability, making it difficult to determine whether predictions are driven by tumor-relevant…

Many functional and structural neuroimaging studies call for accurate morphometric segmentation of different brain structures starting from image intensity values of MRI scans. Current automatic (multi-) atlas-based segmentation strategies…

An increasing amount of collected data are high-dimensional multi-way arrays (tensors), and it is crucial for efficient learning algorithms to exploit this tensorial structure as much as possible. The ever-present curse of dimensionality…

Class activation mapping (CAM) is a widely adopted class of saliency methods used to explain the behavior of convolutional neural networks (CNNs). These methods generate heatmaps that highlight the parts of the input most relevant to the…

The need for Explainable AI is increasing with the development of deep learning. The saliency maps derived from convolutional neural networks generally fail in localizing with accuracy the image features justifying the network prediction.…

Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this CVPR 2015 paper, we discover that a high-quality visual saliency model can be trained with multiscale features…

In this paper, we propose an efficient saliency map generation method, called Group score-weighted Class Activation Mapping (Group-CAM), which adopts the "split-transform-merge" strategy to generate saliency maps. Specifically, for an input…

Deep learning has become a one-size-fits-all solution for technical and business domains thanks to its flexibility and adaptability. It is implemented using opaque models, which unfortunately undermines the outcome trustworthiness. In order…

Researchers have proposed various methods for visually interpreting the Convolutional Neural Network (CNN) via saliency maps, which include Class-Activation-Map (CAM) based approaches as a leading family. However, in terms of the internal…

The opaque nature of deep learning models remains a significant barrier to their clinical adoption in medical imaging. This paper presents a multimodal explainability framework that bridges the gap between convolutional neural network (CNN)…

The explanation for deep neural networks has drawn extensive attention in the deep learning community over the past few years. In this work, we study the visual saliency, a.k.a. visual explanation, to interpret convolutional neural…

Convolutional Neural Networks (CNNs) have been widely employed for image Super-Resolution (SR) in recent years. Various techniques enhance SR performance by altering CNN structures or incorporating improved self-attention mechanisms.…

Various saliency detection algorithms from color images have been proposed to mimic eye fixation or attentive object detection response of human observers for the same scenes. However, developments on hyperspectral imaging systems enable us…

Increasing demands for understanding the internal behavior of convolutional neural networks (CNNs) have led to remarkable improvements in explanation methods. Particularly, several class activation mapping (CAM) based methods, which…

Currently, existing efforts in Weakly Supervised Semantic Segmentation (WSSS) based on Convolutional Neural Networks (CNNs) have predominantly focused on enhancing the multi-label classification network stage, with limited attention given…

Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision problems. However, these deep models are perceived as "black box" methods considering the lack of understanding of their…

Deep learning has become a valuable tool for the automation of certain medical image segmentation tasks, significantly relieving the workload of medical specialists. Some of these tasks require segmentation to be performed on a subset of…

Explainability is a vital aspect of modern AI for real-world impact and usability. The main objective of this paper is to emphasise the need to understand the predictions of Computer Vision models, specifically Convolutional Neural Network…