Zobrazeno 1 - 10
of 238
pro vyhledávání: '"Angelov, Plamen P."'
In this paper, we present a novel diffusion model-based monaural speech enhancement method. Our approach incorporates the separate estimation of speech spectra's magnitude and phase in two diffusion networks. Throughout the diffusion process, noise c
Externí odkaz:
http://arxiv.org/abs/2412.08856
Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised represent
Externí odkaz:
http://arxiv.org/abs/2407.04382
As the use of Deep Neural Networks (DNNs) becomes pervasive, their vulnerability to adversarial attacks and limitations in handling unseen classes poses significant challenges. The state-of-the-art offers discrete solutions aimed to tackle individual
Externí odkaz:
http://arxiv.org/abs/2406.16501
Publikováno v:
ICANN2024
As the development of deep learning techniques in autonomous landing systems continues to grow, one of the major challenges is trust and security in the face of possible adversarial attacks. In this paper, we propose a federated adversarial learning-
Externí odkaz:
http://arxiv.org/abs/2406.15925
Publikováno v:
CVPR2024
Deepfake techniques generate highly realistic data, making it challenging for humans to discern between actual and artificially generated images. Recent advancements in deep learning-based deepfake detection methods, particularly with diffusion model
Externí odkaz:
http://arxiv.org/abs/2406.15921
In this paper, we address two critical challenges in the domain of flood detection: the computational expense of large-scale time series change detection and the lack of interpretable decision-making processes on explainable AI (XAI). To overcome the
Externí odkaz:
http://arxiv.org/abs/2405.07916
Autor:
Kangin, Dmitry, Angelov, Plamen
The vision transformer-based foundation models, such as ViT or Dino-V2, are aimed at solving problems with little or no finetuning of features. Using a setting of prototypical networks, we analyse to what extent such foundation models can solve unsup
Externí odkaz:
http://arxiv.org/abs/2402.14976
The proposed framework named IDEAL (Interpretable-by-design DEep learning ALgorithms) recasts the standard supervised classification problem into a function of similarity to a set of prototypes derived from the training data, while taking advantage o
Externí odkaz:
http://arxiv.org/abs/2311.11396