相关论文: DFIL: Deepfake Incremental Learning by Exploiting …

Domain incremental learning aims to adapt to a sequence of domains with access to only a small subset of data (i.e., memory) from previous domains. Various methods have been proposed for this problem, but it is still unclear how they are…

This paper present a comprehensive comparative analysis of supervised and self-supervised models for deepfake detection. We evaluate eight supervised deep learning architectures and two transformer-based models pre-trained using…

Out-of-distribution generalization is a common problem that expects the model to perform well in the different distributions even far from the train data. A popular approach to addressing this issue is invariant learning (IL), in which the…

Incremental learning is a form of online learning. Incremental learning can modify the parameters and structure of the deep learning model so that the model does not forget the old knowledge while learning new knowledge. Preventing…

Traditional defenses against Deep Leakage (DL) attacks in Federated Learning (FL) primarily focus on obfuscation, introducing noise, transformations or encryption to degrade an attacker's ability to reconstruct private data. While effective…

Class-Incremental Learning (CIL) struggles with catastrophic forgetting when learning new knowledge, and Data-Free CIL (DFCIL) is even more challenging without access to the training data of previously learned classes. Though recent DFCIL…

Deep learning models have achieved state-of-the-art performance in many computer vision tasks. However, in real-world scenarios, novel classes that were unseen during training often emerge, requiring models to acquire new knowledge…

Post-training of flow matching models-aligning the output distribution with a high-quality target-is mathematically equivalent to imitation learning. While Supervised Fine-Tuning mimics expert demonstrations effectively, it cannot correct…

We consider the generic deep image enhancement problem where an input image is transformed into a perceptually better-looking image. Recent methods for image enhancement consider the problem by performing style transfer and image…

In the realm of class-incremental learning (CIL), alleviating the catastrophic forgetting problem is a pivotal challenge. This paper discovers a counter-intuitive observation: by incorporating domain shift into CIL tasks, the forgetting…

Deep neural network (DNN) suffers from catastrophic forgetting when learning incrementally, which greatly limits its applications. Although maintaining a handful of samples (called `exemplars`) of each task could alleviate forgetting to…

We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…

Facial forgery detection is a crucial but extremely challenging topic, with the fast development of forgery techniques making the synthetic artefact highly indistinguishable. Prior works show that by mining both spatial and frequency…

Detecting digital face manipulation in images and video has attracted extensive attention due to the potential risk to public trust. To counteract the malicious usage of such techniques, deep learning-based deepfake detection methods have…

Deep Learning in Image Registration (DLIR) methods have been tremendously successful in image registration due to their speed and ability to incorporate weak label supervision at training time. However, existing DLIR methods forego many of…

Currently, the rapid development of computer vision and deep learning has enabled the creation or manipulation of high-fidelity facial images and videos via deep generative approaches. This technology, also known as deepfake, has achieved…

This paper introduces a novel approach to evaluating deep learning models' capacity for in-diagram logic interpretation. Leveraging the intriguing realm of visual illusions, we establish a unique dataset, InDL, designed to rigorously test…

Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain performance and are therefore prone to learning spurious,…

In this paper, we focus on a new and challenging decentralized machine learning paradigm in which there are continuous inflows of data to be addressed and the data are stored in multiple repositories. We initiate the study of data…

The rise of Deepfake technology to generate hyper-realistic manipulated images and videos poses a significant challenge to the public and relevant authorities. This study presents a robust Deepfake detection based on a modified Vision…