Related papers: Explainable Misinformation Detection Across Multip…

With the explosive growth of the Coronavirus Pandemic (COVID-19), misinformation on social media has developed into a global phenomenon with widespread and detrimental societal effects. Despite recent progress and efforts in detecting…

Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks. Solutions to both problems exist, among others, in the form of counterfactual examples generation to enhance explainability or…

While deep learning models have demonstrated remarkable success in numerous domains, their black-box nature remains a significant limitation, especially in critical fields such as medical image analysis and inference. Existing…

An infodemic refers to an enormous amount of true information and misinformation disseminated during a disease outbreak. Detecting misinformation at the early stage of an infodemic is key to reduce its harm to public health. An early stage…

This article introduces misinfo-general, a benchmark dataset for evaluating misinformation models' ability to perform out-of-distribution generalization. Misinformation changes rapidly, much more quickly than moderators can annotate at…

The proliferation of misinformation in digital platforms reveals the limitations of traditional detection methods, which mostly rely on static classification and fail to capture the intricate process of real-world fact-checking. Despite…

We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from…

Unsupervised domain adaptation aims at transferring knowledge from the labeled source domain to the unlabeled target domain. Previous adversarial domain adaptation methods mostly adopt the discriminator with binary or $K$-dimensional output…

The upheaval brought by the arrival of the COVID-19 pandemic has continued to bring fresh challenges over the past two years. During this COVID-19 pandemic, there has been a need for rapid identification of infected patients and specific…

Domain generalization models aim to learn cross-domain knowledge from source domain data, to improve performance on unknown target domains. Recent research has demonstrated that diverse and rich source domain samples can enhance domain…

Social graph-based fake news detection aims to identify news articles containing false information by utilizing social contexts, e.g., user information, tweets and comments. However, conventional methods are evaluated under less realistic…

Disinformation has long been regarded as a severe social problem, where fake news is one of the most representative issues. What is worse, today's highly developed social media makes fake news widely spread at incredible speed, bringing in…

Supervised learning with large scale labeled datasets and deep layered models has made a paradigm shift in diverse areas in learning and recognition. However, this approach still suffers generalization issues under the presence of a domain…

During the onset of a disaster event, filtering relevant information from the social web data is challenging due to its sparse availability and practical limitations in labeling datasets of an ongoing crisis. In this paper, we hypothesize…

Black-box deep learning approaches have showcased significant potential in the realm of medical image analysis. However, the stringent trustworthiness requirements intrinsic to the medical field have catalyzed research into the utilization…

Although current face anti-spoofing methods achieve promising results under intra-dataset testing, they suffer from poor generalization to unseen attacks. Most existing works adopt domain adaptation (DA) or domain generalization (DG)…

Building generalizable AI models is one of the primary challenges in the healthcare domain. While radiologists rely on generalizable descriptive rules of abnormality, Neural Network (NN) models suffer even with a slight shift in input…

Domain adaptation for object detection (DAOD) has recently drawn much attention owing to its capability of detecting target objects without any annotations. To tackle the problem, previous works focus on aligning features extracted from…

Semantic segmentation models based on convolutional neural networks have recently displayed remarkable performance for a multitude of applications. However, these models typically do not generalize well when applied on new domains,…

In this paper, we tackle the domain adaptive object detection problem, where the main challenge lies in significant domain gaps between source and target domains. Previous work seeks to plainly align image-level and instance-level shifts to…