Related papers: Saliency-driven Class Impressions for Feature Visu…
This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets). We consider two visualisation techniques, based on computing the gradient of the class score with respect to the…
Recently, many methods to interpret and visualize deep neural network predictions have been proposed and significant progress has been made. However, a more class-discriminative and visually pleasing explanation is required. Thus, this…
Interpretability is a critical factor in applying complex deep learning models to advance the understanding of brain disorders in neuroimaging studies. To interpret the decision process of a trained classifier, existing techniques typically…
Neural network visualization techniques mark image locations by their relevancy to the network's classification. Existing methods are effective in highlighting the regions that affect the resulting classification the most. However, as we…
Saliency methods provide post-hoc model interpretation by attributing input features to the model outputs. Current methods mainly achieve this using a single input sample, thereby failing to answer input-independent inquiries about the…
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…
This article presents the prediction difference analysis method for visualizing the response of a deep neural network to a specific input. When classifying images, the method highlights areas in a given input image that provide evidence for…
Deep Neural Networks are powerful tools to understand complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. While online saliency-guided training methods try to…
In deep learning, visualization techniques extract the salient patterns exploited by deep networks for image classification, focusing on single images; no effort has been spent in investigating whether these patterns are systematically…
Understanding specifically where a model focuses on within an image is critical for human interpretability of the decision-making process. Deep learning-based solutions are prone to learning coincidental correlations in training datasets,…
Interactive Machine Teaching systems allow users to create customized machine learning models through an iterative process of user-guided training and model assessment. They primarily offer confidence scores of each label or class as…
Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this paper, we discover that a high-quality visual saliency model can be learned from multiscale features extracted using…
Saliency methods have been widely used to highlight important input features in model predictions. Most existing methods use backpropagation on a modified gradient function to generate saliency maps. Thus, noisy gradients can result in…
Recently, data-driven deep saliency models have achieved high performance and have outperformed classical saliency models, as demonstrated by results on datasets such as the MIT300 and SALICON. Yet, there remains a large gap between the…
In this paper, we present contemporary techniques for visualising the feature space of a deep learning image classification neural network. These techniques are viewed in the context of a feed-forward network trained to classify low…
In this paper, we show that existing recognition and localization deep architectures, that have not been exposed to eye tracking data or any saliency datasets, are capable of predicting the human visual saliency. We term this as implicit…
Currently available methods for extracting saliency maps identify parts of the input which are the most important to a specific fixed classifier. We show that this strong dependence on a given classifier hinders their performance. To…
Classic feature selection techniques remove those features that are either irrelevant or redundant, achieving a subset of relevant features that help to provide a better knowledge extraction. This allows the creation of compact models that…
Despite the huge success of deep convolutional neural networks in face recognition (FR) tasks, current methods lack explainability for their predictions because of their "black-box" nature. In recent years, studies have been carried out to…
Transparency and explainability in image classification are essential for establishing trust in machine learning models and detecting biases and errors. State-of-the-art explainability methods generate saliency maps to show where a specific…