Related papers: Open-World Deepfake Attribution via Confidence-Awa…

Confidence calibration is of great importance to the reliability of decisions made by machine learning systems. However, discriminative classifiers based on deep neural networks are often criticized for producing overconfident predictions…

Facial forgery by deepfakes has caused major security risks and raised severe societal concerns. As a countermeasure, a number of deepfake detection methods have been proposed. Most of them model deepfake detection as a binary…

Open-World Continual Learning (OWCL) is a challenging paradigm where models must incrementally learn new knowledge without forgetting while operating under an open-world assumption. This requires handling incomplete training data and…

Current diffusion-based makeup transfer methods commonly use the makeup information encoded by off-the-shelf foundation models (e.g., CLIP) as condition to preserve the makeup style of reference image in the generation. Although effective,…

Image editing techniques enable people to modify the content of an image without leaving visual traces and thus may cause serious security risks. Hence the detection and localization of these forgeries become quite necessary and…

Detecting partial deepfake speech is essential due to its potential for subtle misinformation. However, existing methods depend on costly frame-level annotations during training, limiting real-world scalability. Also, they focus on…

In practical machine learning applications, it is often challenging to assign accurate labels to data, and increasing the number of labeled instances is often limited. In such cases, Weakly Supervised Learning (WSL), which enables training…

Anomaly detection in time-series data is crucial for identifying faults, failures, threats, and outliers across a range of applications. Recently, deep learning techniques have been applied to this topic, but they often struggle in…

The rapid evolution of deepfake technologies demands robust and reliable face forgery detection algorithms. While determining whether an image has been manipulated remains essential, the ability to precisely localize forgery clues is also…

Self-supervised learning methods learn high-quality visual representations, yet recent studies show that these representations often capture demographic biases present in the training data. Existing fairness-aware methods address this by…

The rapid advancement of generative AI has enabled the mass production of photorealistic synthetic images, blurring the boundary between authentic and fabricated visual content. This challenge is particularly evident in deepfake scenarios…

Real-world DeepFake videos often undergo various compression operations, resulting in a range of video qualities. These varying qualities diversify the pattern of forgery traces, significantly increasing the difficulty of DeepFake…

Continual Learning (CL) aims to enable Deep Neural Networks (DNNs) to learn new data without forgetting previously learned knowledge. The key to achieving this goal is to avoid confusion at the feature level, i.e., avoiding confusion within…

Deep learning models, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), have achieved state-of-the-art performance on various computer vision tasks such as object classification, detection, segmentation,…

Deep learning models often achieve expert-level accuracy in medical image classification but suffer from a critical flaw: semantic incoherence. These high-confidence mistakes that are semantically incoherent (e.g., classifying a malignant…

Reliable confidence estimation is a challenging yet fundamental requirement in many risk-sensitive applications. However, modern deep neural networks are often overconfident for their incorrect predictions, i.e., misclassified samples from…

In the active learning paradigm, using an oracle to label data has always been a complex and expensive task, and with the emersion of large unlabeled data pools, it would be highly beneficial If we could achieve better results without…

The proliferation of sophisticated AI-generated deepfakes poses critical challenges for digital media authentication and societal security. While existing detection methods perform well within specific generative domains, they exhibit…

Modern deepfake detectors have achieved encouraging results, when training and test images are drawn from the same data collection. However, when these detectors are applied to images produced with unknown deepfake-generation techniques,…

Open-Set Domain Adaptation (OSDA) assumes that a target domain contains unknown classes, which are not discovered in a source domain. Existing domain adversarial learning methods are not suitable for OSDA because distribution matching with…