Related papers: Global Saliency: Aggregating Saliency Maps to Asse…

Saliency methods are a popular class of feature attribution explanation methods that aim to capture a model's predictive reasoning by identifying "important" pixels in an input image. However, the development and adoption of these methods…

The widespread adoption of machine learning systems has raised critical concerns about fairness and bias, making mitigating harmful biases essential for AI development. In this paper, we investigate the relationship between debiasing and…

Realizing when a model is right for a wrong reason is not trivial and requires a significant effort by model developers. In some cases an input salience method, which highlights the most important parts of the input, may reveal problematic…

Research in interpretable machine learning proposes different computational and human subject approaches to evaluate model saliency explanations. These approaches measure different qualities of explanations to achieve diverse goals in…

Incorporating human-perceptual intelligence into model training has shown to increase the generalization capability of models in several difficult biometric tasks, such as presentation attack detection (PAD) and detection of synthetic…

Omni-directional images have been used in wide range of applications. For the applications, it would be useful to estimate saliency maps representing probability distributions of gazing points with a head-mounted display, to detect…

A fundamental bottleneck in utilising complex machine learning systems for critical applications has been not knowing why they do and what they do, thus preventing the development of any crucial safety protocols. To date, no method exist…

Saliency maps are often used in computer vision to provide intuitive interpretations of what input regions a model has used to produce a specific prediction. A number of approaches to saliency map generation are available, but most require…

In recent years, considerable work has been devoted to explaining predictive, deep learning-based models, and in turn how to evaluate explanations. An important class of evaluation methods are ones that are human-centered, which typically…

Saliency detection has drawn a lot of attention of researchers in various fields over the past several years. Saliency is the perceptual quality that makes an object, person to draw the attention of humans at the very sight. Salient object…

Deep learning models are now used in many different industries, while in certain domains safety is not a critical issue in the medical field it is a huge concern. Not only, we want the models to generalize well but we also want to know the…

The introduction of saliency map algorithms as an approach for assessing the interoperability of images has allowed for a deeper understanding of current black-box models with Artificial Intelligence. Their rise in popularity has led to…

Deep neural networks have shown their profound impact on achieving human level performance in visual saliency prediction. However, it is still unclear how they learn the task and what it means in terms of understanding human visual system.…

We consider machine-learning-based malignancy prediction and lesion identification from clinical dermatological images, which can be indistinctly acquired via smartphone or dermoscopy capture. Additionally, we do not assume that images…

We describe an explainable AI saliency map method for use with deep convolutional neural networks (CNN) that is much more efficient than popular fine-resolution gradient methods. It is also quantitatively similar or better in accuracy. Our…

As the demand for interpretable machine learning approaches continues to grow, there is an increasing necessity for human involvement in providing informative explanations for model decisions. This is necessary for building trust and…

Given a grayscale photograph, the colorization system estimates a visually plausible colorful image. Conventional methods often use semantics to colorize grayscale images. However, in these methods, only classification semantic information…

Improving the interpretability of geospatial artificial intelligence (GeoAI) models has become critically important to open the "black box" of complex AI models, such as deep learning. This paper compares popular saliency map generation…

Feature maps in deep neural network generally contain different semantics. Existing methods often omit their characteristics that may lead to sub-optimal results. In this paper, we propose a novel end-to-end deep saliency network which…

There have been remarkable improvements in the semantic labelling task in the recent years. However, the state of the art methods rely on large-scale pixel-level annotations. This paper studies the problem of training a pixel-wise semantic…