Related papers: Aligning Eyes between Humans and Deep Neural Netwo…

Diabetes is one of the most common disease in individuals. \textit{Diabetic retinopathy} (DR) is a complication of diabetes, which could lead to blindness. Automatic DR grading based on retinal images provides a great diagnostic and…

Nowadays, a huge number of images are available. However, retrieving a required image for an ordinary user is a challenging task in computer vision systems. During the past two decades, many types of research have been introduced to improve…

While deep learning has significantly improved ReID model accuracy under the independent and identical distribution (IID) assumption, it has also become clear that such models degrade notably when applied to an unseen novel domain due to…

In coming years or decades, artificial general intelligence (AGI) may surpass human capabilities across many critical domains. We argue that, without substantial effort to prevent it, AGIs could learn to pursue goals that are in conflict…

False data injection attacks (FDIAs) pose a significant security threat to power system state estimation. To detect such attacks, recent studies have proposed machine learning (ML) techniques, particularly deep neural networks (DNNs).…

There are an increasing number of domains in which artificial intelligence (AI) systems both surpass human ability and accurately model human behavior. This introduces the possibility of algorithmically-informed teaching in these domains…

We address the problem of visual storytelling, i.e., generating a story for a given sequence of images. While each sentence of the story should describe a corresponding image, a coherent story also needs to be consistent and relate to both…

In computer vision, the performance of deep neural networks (DNNs) is highly related to the feature extraction ability, i.e., the ability to recognize and focus on key pixel regions in an image. However, in this paper, we quantitatively and…

Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt…

Despite the recent, widespread focus on eXplainable AI (XAI), explanations computed by XAI methods tend to provide little insight into the functioning of Neural Networks (NNs). We propose a novel framework for obtaining (local) explanations…

Large language models (LLMs) have demonstrated technical accuracy in high-risk domains, such as mental health support and special education. However, they often fail to meet the nuanced behavioral expectations of domain experts. This gap…

Convolutional Neural Networks (CNNs) frequently "cheat" by exploiting superficial correlations, raising concerns about whether they make predictions for the right reasons. Inspired by cognitive science, which highlights the role of…

Recent advances in general-purpose AI underscore the urgent need to align AI systems with human goals and values. Yet, the lack of a clear, shared understanding of what constitutes "alignment" limits meaningful progress and…

Nowadays, Deep Learning as a service can be deployed in Internet of Things (IoT) to provide smart services and sensor data processing. However, recent research has revealed that some Deep Neural Networks (DNN) can be easily misled by adding…

In this paper, we present two approaches and algorithms that adapt areas of interest We present a new deep neural network (DNN) that can be used to directly determine gaze position using EEG data. EEG-based eye tracking is a new and…

This work aligns deep learning (DL) with human reasoning capabilities and needs to enable more efficient, interpretable, and robust image classification. We approach this from three perspectives: explainability, causality, and biological…

White-box Adversarial Example (AE) attacks towards Deep Neural Networks (DNNs) have a more powerful destructive capacity than black-box AE attacks in the fields of AE strategies. However, almost all the white-box approaches lack…

Providing explanations for deep neural networks (DNNs) is essential for their use in domains wherein the interpretability of decisions is a critical prerequisite. Despite the plethora of work on interpreting DNNs, most existing solutions…

Endowing robots with human-like physical reasoning abilities remains challenging. We argue that existing methods often disregard spatio-temporal relations and by using Graph Neural Networks (GNNs) that incorporate a relational inductive…

The last decade of machine learning has seen drastic increases in scale and capabilities. Deep neural networks (DNNs) are increasingly being deployed in the real world. However, they are difficult to analyze, raising concerns about using…