Related papers: FReTAL: Generalizing Deepfake Detection using Know…

Generative Adversarial Networks (GANs) rely heavily on large-scale training data for training high-quality image generation models. With limited training data, the GAN discriminator often suffers from severe overfitting which directly leads…

The challenge in sourcing attribution for forgery faces has gained widespread attention due to the rapid development of generative techniques. While many recent works have taken essential steps on GAN-generated faces, more threatening…

Federated learning (FL) enables a decentralized machine learning paradigm for multiple clients to collaboratively train a generalized global model without sharing their private data. Most existing works simply propose typical FL systems for…

Deepfakes are the synthesized digital media in order to create ultra-realistic fake videos to trick the spectator. Deep generative algorithms, such as, Generative Adversarial Networks(GAN) are widely used to accomplish such tasks. This…

Residual-domain feature is very useful for Deepfake detection because it suppresses irrelevant content features and preserves key manipulation traces. However, inappropriate residual prediction will bring side effects on detection accuracy.…

In the surveillance and defense domain, multi-target detection and classification (MTD) is considered essential yet challenging due to heterogeneous inputs from diverse data sources and the computational complexity of algorithms designed…

Model compression and knowledge distillation have been successfully applied for cross-architecture and cross-domain transfer learning. However, a key requirement is that training examples are in correspondence across the domains. We show…

Knowledge distillation (KD) aims to transfer the knowledge of a more capable yet cumbersome teacher model to a lightweight student model. In recent years, relation-based KD methods have fallen behind, as their instance-matching counterparts…

Reinforcement learning (RL) is well known for requiring large amounts of data in order for RL agents to learn to perform complex tasks. Recent progress in model-based RL allows agents to be much more data-efficient, as it enables them to…

Performance achievable by modern deep learning approaches are directly related to the amount of data used at training time. Unfortunately, the annotation process is notoriously tedious and expensive, especially for pixel-wise tasks like…

Face swapping technology used to create "Deepfakes" has advanced significantly over the past few years and now enables us to create realistic facial manipulations. Current deep learning algorithms to detect deepfakes have shown promising…

As a general model compression paradigm, feature-based knowledge distillation allows the student model to learn expressive features from the teacher counterpart. In this paper, we mainly focus on designing an effective feature-distillation…

We propose a learning framework named Feature Fusion Learning (FFL) that efficiently trains a powerful classifier through a fusion module which combines the feature maps generated from parallel neural networks. Specifically, we train a…

This study proposes a knowledge distillation algorithm based on large language models and feature alignment, aiming to effectively transfer the knowledge of large pre-trained models into lightweight student models, thereby reducing…

Building facial analysis systems that generalize to extreme variations in lighting and facial expressions is a challenging problem that can potentially be alleviated using natural-looking synthetic data. Towards that, we propose LEGAN, a…

The performance of a convolutional neural network (CNN) based face recognition model largely relies on the richness of labelled training data. Collecting a training set with large variations of a face identity under different poses and…

Face forgery by deepfake is widely spread over the internet and this raises severe societal concerns. In this paper, we propose a novel video transformer with incremental learning for detecting deepfake videos. To better align the input…

As deep learning models grow in complexity and the volume of training data increases, reducing storage and computational costs becomes increasingly important. Dataset distillation addresses this challenge by synthesizing a compact set of…

Knowledge distillation (KD) is the process of transferring knowledge from a large model to a small one. It has gained increasing attention in the natural language processing community, driven by the demands of compressing ever-growing…

Knowledge distillation is a powerful technique for transferring knowledge from a pre-trained teacher model to a student model. However, the true potential of knowledge transfer has not been fully explored. Existing approaches primarily…