Zobrazeno 1 - 10
of 6 218
pro vyhledávání: '"li, Hongwei"'
Deep learning-based image denoising models demonstrate remarkable performance, but their lack of robustness analysis remains a significant concern. A major issue is that these models are susceptible to adversarial attacks, where small, carefully craf
Externí odkaz:
http://arxiv.org/abs/2412.05943
Autor:
Jiang, Wenbo, He, Jiaming, Li, Hongwei, Xu, Guowen, Zhang, Rui, Chen, Hanxiao, Hao, Meng, Yang, Haomiao
Recently, Text-to-Image (T2I) synthesis technology has made tremendous strides. Numerous representative T2I models have emerged and achieved promising application outcomes, such as DALL-E, Stable Diffusion, Imagen, etc. In practice, it has become inc
Externí odkaz:
http://arxiv.org/abs/2411.12389
Understanding the interplay of non-Hermiticity and topology is crucial given the intrinsic openness of most natural and engineered systems and it has important ramifications in topological lasers and sensors. Intense efforts have been devoted to unve
Externí odkaz:
http://arxiv.org/abs/2411.08729
Recently, the success of Text-to-Image (T2I) models has led to the rise of numerous third-party platforms, which claim to provide cheaper API services and more flexibility in model options. However, this also raises a new security concern: Are these
Externí odkaz:
http://arxiv.org/abs/2410.22725
Vision Transformers (ViTs) have outperformed traditional Convolutional Neural Networks (CNN) across various computer vision tasks. However, akin to CNN, ViTs are vulnerable to backdoor attacks, where the adversary embeds the backdoor into the victim
Externí odkaz:
http://arxiv.org/abs/2410.22678
Deep-learning methods have shown promising performance for low-dose computed tomography (LDCT) reconstruction. However, supervised methods face the problem of lacking labeled data in clinical scenarios, and the CNN-based unsupervised denoising method
Externí odkaz:
http://arxiv.org/abs/2410.17543
Autor:
Pérez-Bueno, Fernando, Li, Hongwei Bran, Nasr, Shahin, Caballero-Gaudes, Cesar, Iglesias, Juan Eugenio
While functional Magnetic Resonance Imaging (fMRI) offers valuable insights into cognitive processes, its inherent spatial limitations pose challenges for detailed analysis of the fine-grained functional architecture of the brain. More specifically,
Externí odkaz:
http://arxiv.org/abs/2410.04097
The expansive storage capacity and robust computational power of cloud servers have led to the widespread outsourcing of machine learning inference services to the cloud. While this practice offers significant operational benefits, it also poses subs
Externí odkaz:
http://arxiv.org/abs/2409.19334
Autor:
Yuan, Shuai, Li, Hongwei, Han, Xingshuo, Xu, Guowen, Jiang, Wenbo, Ni, Tao, Zhao, Qingchuan, Fang, Yuguang
Physical adversarial patches have emerged as a key adversarial attack to cause misclassification of traffic sign recognition (TSR) systems in the real world. However, existing adversarial patches have poor stealthiness and attack all vehicles indiscr
Externí odkaz:
http://arxiv.org/abs/2409.12394
Autor:
Hu, Qingqiao, Zhang, Daoan, Luo, Jiebo, Gong, Zhenyu, Wiestler, Benedikt, Zhang, Jianguo, Li, Hongwei Bran
Learning meaningful and interpretable representations from high-dimensional volumetric magnetic resonance (MR) images is essential for advancing personalized medicine. While Vision Transformers (ViTs) have shown promise in handling image data, their
Externí odkaz:
http://arxiv.org/abs/2409.07746