相关论文: Shared Interest: Measuring Human-AI Alignment to I…

A deep feature based saliency model (DeepFeat) is developed to leverage the understanding of the prediction of human fixations. Traditional saliency models often predict the human visual attention relying on few level image cues. Although…

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…

There is growing interest in incorporating eye-tracking data and other implicit measures of human language processing into natural language processing (NLP) pipelines. The data from human language processing contain unique insight into…

Privacy preservation is a crucial component of any real-world application. But, in applications relying on machine learning backends, privacy is challenging because models often capture more than what the model was initially trained for,…

Photo collections and its applications today attempt to reflect user interactions in various forms. Moreover, photo collections aim to capture the users' intention with minimum effort through applications capturing user intentions. Human…

Decision processes of computer vision models - especially deep neural networks - are opaque in nature, meaning that these decisions cannot be understood by humans. Thus, over the last years, many methods to provide human-understandable…

In high-stakes applications of machine learning models, interpretability methods provide guarantees that models are right for the right reasons. In medical imaging, saliency maps have become the standard tool for determining whether a…

Understanding the reasons behind the predictions made by deep neural networks is critical for gaining human trust in many important applications, which is reflected in the increasing demand for explainability in AI (XAI) in recent years.…

Precise user modeling is critical for online personalized recommendation services. Generally, users' interests are diverse and are not limited to a single aspect, which is particularly evident when their behaviors are observed for a longer…

Saliency methods can make deep neural network predictions more interpretable by identifying a set of critical features in an input sample, such as pixels that contribute most strongly to a prediction made by an image classifier.…

Existing saliency-guided training approaches improve model generalization by incorporating a loss term that compares the model's class activation map (CAM) for a sample's true-class ({\it i.e.}, correct-label class) against a human…

We describe a context-sensitive model of choice, in which the selection process is shaped not only by the attractiveness of items but also by their semantics ('salience'). All items are ranked according to a relation of salience, and a…

Chain-of-thought (CoT) prompting has been shown to empirically improve the accuracy of large language models (LLMs) on various question answering tasks. While understanding why CoT prompting is effective is crucial to ensuring that this…

Forecasting tasks surrounding the dynamics of low-level human behavior are of significance to multiple research domains. In such settings, methods for explaining specific forecasts can enable domain experts to gain insights into the…

Human attention is the gateway to conscious perception, memory and decision-making. However, its role in modern transformer models remains largely unexplored. As these systems increasingly influence what people see, prefer and buy, the…

Saliency prediction is a well studied problem in computer vision. Early saliency models were based on low-level hand-crafted feature derived from insights gained in neuroscience and psychophysics. In the wake of deep learning breakthrough,…

One of the motivations for explainable AI is to allow humans to make better and more informed decisions regarding the use and deployment of AI models. But careful evaluations are needed to assess whether this expectation has been fulfilled.…

Bottom-up saliency, an early human visual processing, behaves like binary classification of interest and null hypothesis. Its discriminant power, mutual information of image features and class distribution, is closely related to saliency…

Most social network analysis works at the level of interactions between users. But the vast growth in size and complexity of social networks enables us to examine interactions at larger scale. In this work we use a dataset of 76M…

Discovering relevant patterns for a particular user remains a challenging tasks in data mining. Several approaches have been proposed to learn user-specific pattern ranking functions. These approaches generalize well, but at the expense of…