Energy-guided entropic neural optimal transport
P Mokrov, A Korotin, A Kolesov, N Gushchin… - ar** new realities: Ground truth image creation with pix2pix image-to-image translation
Generative Adversarial Networks (GANs) have significantly advanced image processing,
with Pix2Pix being a notable framework for image-to-image translation. This paper explores …
with Pix2Pix being a notable framework for image-to-image translation. This paper explores …
Learning energy-based models by cooperative diffusion recovery likelihood
Training energy-based models (EBMs) with maximum likelihood estimation on high-
dimensional data can be both challenging and time-consuming. As a result, there a …
dimensional data can be both challenging and time-consuming. As a result, there a …
EGC: Image Generation and Classification via a Diffusion Energy-Based Model
Learning image classification and image generation using the same set of network
parameters presents a formidable challenge. Recent advanced approaches perform well in …
parameters presents a formidable challenge. Recent advanced approaches perform well in …
CAGAN: Constrained neural architecture search for GANs
Recently, a number of Neural Architecture Search (NAS) methods have been proposed to
automate the design of Generative Adversarial Networks (GANs). However, due to the …
automate the design of Generative Adversarial Networks (GANs). However, due to the …
Towards Robust Adversarial Purification for Face Recognition under Intensity-Unknown Attacks
K Xu, Z Chen, Z Wang, C **ao… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Recent years have witnessed dramatic progress in adversarial attacks, which can easily
mislead face recognition systems via the injection of imperceptible perturbations on the input …
mislead face recognition systems via the injection of imperceptible perturbations on the input …
Out-of-Distribution Data: An Acquaintance of Adversarial Examples--A Survey
Deep neural networks (DNNs) deployed in real-world applications can encounter out-of-
distribution (OOD) data and adversarial examples. These represent distinct forms of …
distribution (OOD) data and adversarial examples. These represent distinct forms of …
Generative Robust Classification
X Yin - arxiv preprint arxiv:2212.07283, 2022 - arxiv.org
Training adversarially robust discriminative (ie, softmax) classifier has been the dominant
approach to robust classification. Building on recent work on adversarial training (AT)-based …
approach to robust classification. Building on recent work on adversarial training (AT)-based …
Robust out-of-distribution detection in deep classifiers
A Meinke - 2023 - ub01.uni-tuebingen.de
Over the past decade, deep learning has gone from a fringe discipline of computer science
to a major driver of innovation across a large number of industries. The deployment of such …
to a major driver of innovation across a large number of industries. The deployment of such …