相关论文: Real-Aware Residual Model Merging for Deepfake Det…

Model merging has attracted attention as an effective path toward multi-task adaptation by integrating knowledge from multiple task-specific models. Among existing approaches, dynamic merging mitigates performance degradation caused by…

Detecting falsified faces generated by Deepfake technology is essential for safeguarding trust in digital communication and protecting individuals. However, current detectors often suffer from a dual-overfitting: they become overly…

The rapid advancement of facial forgery techniques poses severe threats to public trust and information security, making facial DeepFake detection a critical research priority. Continual learning provides an effective approach to adapt…

Deepfakes are AI-synthesized multimedia data that may be abused for spreading misinformation. Deepfake generation involves both visual and audio manipulation. To detect audio-visual deepfakes, previous studies commonly employ two relatively…

In causal matching designs, some control subjects are often left unmatched, and some covariates are often left unmodeled. This article introduces "rebar," a method using high-dimensional modeling to incorporate these commonly discarded data…

We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks…

Model merging provides a cost-effective and data-efficient combination of specialized deep neural networks through parameter integration. This technique leverages expert models across downstream tasks without requiring retraining. Most…

Model merging offers an efficient way to combine pre-trained neural networks but often suffers from inconsistent performance, especially when merging models with different initializations. We identify the ``vanishing feature'' phenomenon,…

Traditional deepfake detectors have dealt with the detection problem as a binary classification task. This approach can achieve satisfactory results in cases where samples of a given deepfake generation technique have been seen during…

Model merging aims to combine multiple task-specific expert models into a single model while preserving generalization across diverse tasks. However, interference among experts, especially when they are trained on different objectives,…

The rapid advancement of generative models has introduced serious risks, including deepfake techniques for facial synthesis and editing. Traditional approaches rely on training classifiers and enhancing generalizability through various…

Face forgery by deepfake is widely spread over the internet and has raised severe societal concerns. Recently, how to detect such forgery contents has become a hot research topic and many deepfake detection methods have been proposed. Most…

Model merging provides a way of cheaply combining individual models to produce a model that inherits each individual's capabilities. While some merging methods can approach the performance of multitask training, they are often heuristically…

Finite Mixture Regression (FMR) refers to the mixture modeling scheme which learns multiple regression models from the training data set. Each of them is in charge of a subset. FMR is an effective scheme for handling sample heterogeneity,…

The rapid evolution of deepfake generation technologies poses critical challenges for detection systems, as non-continual learning methods demand frequent and expensive retraining. We reframe deepfake detection (DFD) as a Continual Learning…

Overfitting in deep neural networks occurs less frequently than expected. This is a puzzling observation, as theory predicts that greater model capacity should eventually lead to overfitting -- yet this is rarely seen in practice. But what…

Multivariate time-series modeling and forecasting is an important problem with numerous applications. Traditional approaches such as VAR (vector auto-regressive) models and more recent approaches such as RNNs (recurrent neural networks) are…

The generalization problem is broadly recognized as a critical challenge in detecting deepfakes. Most previous work believes that the generalization gap is caused by the differences among various forgery methods. However, our investigation…

Graph autoencoders are efficient at embedding graph-based data sets. Most graph autoencoder architectures have shallow depths which limits their ability to capture meaningful relations between nodes separated by multi-hops. In this paper,…

In this paper, we study multi-target domain adaptation of scene understanding models. While previous methods achieved commendable results through inter-domain consistency losses, they often assumed unrealistic simultaneous access to images…