Related papers: DiffGradCAM: A Class Activation Map Using the Full…

To have a better understanding and usage of Convolution Neural Networks (CNNs), the visualization and interpretation of CNNs has attracted increasing attention in recent years. In particular, several Class Activation Mapping (CAM) methods…

Neural models of code have shown impressive results when performing tasks such as predicting method names and identifying certain kinds of bugs. We show that these models are vulnerable to adversarial examples, and introduce a novel…

Convolutional neural networks have been shown to develop internal representations, which correspond closely to semantically meaningful objects and parts, although trained solely on class labels. Class Activation Mapping (CAM) is a recent…

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…

Convolutional neural networks (CNNs) achieve prevailing results in segmentation tasks nowadays and represent the state-of-the-art for image-based analysis. However, the understanding of the accurate decision-making process of a CNN is…

Recently many methods have been introduced to explain CNN decisions. However, it has been shown that some methods can be sensitive to manipulation of the input. We continue this line of work and investigate the explanation method GradCAM.…

Targeting solutions over `flat' regions of the loss landscape, sharpness-aware minimization (SAM) has emerged as a powerful tool to improve generalizability of deep neural network based learning. While several SAM variants have been…

In this work, we show that saturating output activation functions, such as the softmax, impede learning on a number of standard classification tasks. Moreover, we present results showing that the utility of softmax does not stem from the…

Class Activation Mapping (CAM) methods are widely used to generate visual explanations for deep learning classifiers in medical imaging. However, existing evaluation frameworks assess whether explanations are correct, measured by…

Compared with expensive pixel-wise annotations, image-level labels make it possible to learn semantic segmentation in a weakly-supervised manner. Within this pipeline, the class activation map (CAM) is obtained and further processed to…

Real-world visual recognition problems often exhibit long-tailed distributions, where the amount of data for learning in different categories shows significant imbalance. Standard classification models learned on such data distribution…

Given their substantial success in addressing a wide range of computer vision challenges, Convolutional Neural Networks (CNNs) are increasingly being used in smart home applications, with many of these applications relying on the automatic…

Sharpness-Aware Minimization (SAM) is a recent training method that relies on worst-case weight perturbations which significantly improves generalization in various settings. We argue that the existing justifications for the success of SAM…

This study proposes a method for imbalanced data classification based on deep probabilistic graphical models (DPGMs) to solve the problem that traditional methods have insufficient learning ability for minority class samples. To address the…

Saliency methods seek to explain the predictions of a model by producing an importance map across each input sample. A popular class of such methods is based on backpropagating a signal and analyzing the resulting gradient. Despite much…

Constraining deep neural networks (DNNs) to learn individual logic types per node, as performed using the DiffLogic network architecture, opens the door to model-specific explanation techniques that quell the complexity inherent to DNNs.…

Deep neural networks have been shown to be fooled rather easily using adversarial attack algorithms. Practical methods such as adversarial patches have been shown to be extremely effective in causing misclassification. However, these…

While Deep Reinforcement Learning (DRL) has emerged as a promising solution for intricate control tasks, the lack of explainability of the learned policies impedes its uptake in safety-critical applications, such as automated driving…

Deep neural networks (DNNs) are being increasingly used to make predictions from functional magnetic resonance imaging (fMRI) data. However, they are widely seen as uninterpretable "black boxes", as it can be difficult to discover what…

Non-intrusive Load Monitoring (NILM) algorithms, commonly referred to as load disaggregation algorithms, are fundamental tools for effective energy management. Despite the success of deep models in load disaggregation, they face various…