Related papers: Diffusion Reconstruction towards Generalizable Aud…
Audio deepfake detection (ADD) is crucial to combat the misuse of speech synthesized from generative AI models. Existing ADD models suffer from generalization issues, with a large performance discrepancy between in-domain and out-of-domain…
Deep learning (DL) methods typically require large datasets to effectively learn data distributions. However, in the medical field, data is often limited in quantity, and acquiring labeled data can be costly. To mitigate this data scarcity,…
Vessel segmentation in medical images is one of the important tasks in the diagnosis of vascular diseases and therapy planning. Although learning-based segmentation approaches have been extensively studied, a large amount of ground-truth…
In the context of continuously rising global air traffic, efficient and safe Conflict Detection and Resolution (CD&R) is paramount for air traffic management. Although Deep Reinforcement Learning (DRL) offers a promising pathway for CD&R…
Deepfake detection models face two critical challenges: generalization to unseen manipulations and demographic fairness among population groups. However, existing approaches often demonstrate that these two objectives are inherently…
Audio plays a crucial role in applications like speaker verification, voice-enabled smart devices, and audio conferencing. However, audio manipulations, such as deepfakes, pose significant risks by enabling the spread of misinformation. Our…
Traditional speech enhancement methods often oversimplify the task of restoration by focusing on a single type of distortion. Generative models that handle multiple distortions frequently struggle with phone reconstruction and…
Despite consistent advancement in powerful deep learning techniques in recent years, large amounts of training data are still necessary for the models to avoid overfitting. Synthetic datasets using generative adversarial networks (GAN) have…
Urban scene reconstruction from real-world observations has emerged as a powerful tool for self-driving development and testing. While current neural rendering approaches achieve high-fidelity rendering along the recorded trajectories,…
Low-field to high-field MRI synthesis has emerged as a cost-effective strategy to enhance image quality under hardware and acquisition constraints, particularly in scenarios where access to high-field scanners is limited or impractical.…
Audio inpainting aims to reconstruct missing segments in corrupted recordings. Most of existing methods produce plausible reconstructions when the gap lengths are short, but struggle to reconstruct gaps larger than about 100 ms. This paper…
This paper introduces a discrete diffusion model (DDM) framework for text-aligned speech tokenization and reconstruction. By replacing the auto-regressive speech decoder with a discrete diffusion counterpart, our model achieves…
We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while maintaining high image quality. We use score distillation to…
Facial manipulation by deep fake has caused major security risks and raised severe societal concerns. As a countermeasure, a number of deep fake detection methods have been proposed recently. Most of them model deep fake detection as a…
Anomaly detection aims to identify samples that deviate from the nominal data distribution and is central to many safety-critical applications. However, developing effective anomaly detection methods for categorical, mixed-type, and…
Discriminative Dictionary Learning (DL) methods have been widely advocated for image classification problems. To further sharpen their discriminative capabilities, most state-of-the-art DL methods have additional constraints included in the…
The rapid progress in generative models has given rise to the critical task of AI-Generated Content Stealth (AIGC-S), which aims to create AI-generated images that can evade both forensic detectors and human inspection. This task is crucial…
Deepfake detection remains a challenging task due to the difficulty of generalizing to new types of forgeries. This problem primarily stems from the overfitting of existing detection methods to forgery-irrelevant features and…
Blind face restoration usually synthesizes degraded low-quality data with a pre-defined degradation model for training, while more complex cases could happen in the real world. This gap between the assumed and actual degradation hurts the…
The malicious use and widespread dissemination of deepfake pose a significant crisis of trust. Current deepfake detection models can generally recognize forgery images by training on a large dataset. However, the accuracy of detection…