Zobrazeno 1 - 10
of 7 086
pro vyhledávání: '"Asif, M."'
Diffusion models can generate a variety of high-quality images by modeling complex data distributions. Trained diffusion models can also be very effective image priors for solving inverse problems. Most of the existing diffusion-based methods integra
Externí odkaz:
http://arxiv.org/abs/2409.08906
Unauthorized privacy-related and copyrighted content generation using generative-AI is becoming a significant concern for human society, raising ethical, legal, and privacy issues that demand urgent attention. The EU's General Data Protection Regulat
Externí odkaz:
http://arxiv.org/abs/2407.11867
We introduce transformation-dependent adversarial attacks, a new class of threats where a single additive perturbation can trigger diverse, controllable mis-predictions by systematically transforming the input (e.g., scaling, blurring, compression).
Externí odkaz:
http://arxiv.org/abs/2406.08443
Autor:
Chakraborty, Trishna, Shayegani, Erfan, Cai, Zikui, Abu-Ghazaleh, Nael, Asif, M. Salman, Dong, Yue, Roy-Chowdhury, Amit K., Song, Chengyu
Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT) and Reinf
Externí odkaz:
http://arxiv.org/abs/2406.02575
The primary focus of Neural Representation for Videos (NeRV) is to effectively model its spatiotemporal consistency. However, current NeRV systems often face a significant issue of spatial inconsistency, leading to decreased perceptual quality. To ad
Externí odkaz:
http://arxiv.org/abs/2404.08921
Publikováno v:
2023 IEEE 9th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2023, pg. 186-190
Plug-and-Play Priors (PnP) is a well-known class of methods for solving inverse problems in computational imaging. PnP methods combine physical forward models with learned prior models specified as image denoisers. A common issue with the learned mod
Externí odkaz:
http://arxiv.org/abs/2403.10374
Autor:
Lal, Rohit, Bachu, Saketh, Garg, Yash, Dutta, Arindam, Ta, Calvin-Khang, Raychaudhuri, Dripta S., Cruz, Hannah Dela, Asif, M. Salman, Roy-Chowdhury, Amit K.
The capability to accurately estimate 3D human poses is crucial for diverse fields such as action recognition, gait recognition, and virtual/augmented reality. However, a persistent and significant challenge within this field is the accurate predicti
Externí odkaz:
http://arxiv.org/abs/2312.16221
Deep learning-based methods deliver state-of-the-art performance for solving inverse problems that arise in computational imaging. These methods can be broadly divided into two groups: (1) learn a network to map measurements to the signal estimate, w
Externí odkaz:
http://arxiv.org/abs/2310.06235
Multi-task and multi-domain learning methods seek to learn multiple tasks/domains, jointly or one after another, using a single unified network. The key challenge and opportunity is to exploit shared information across tasks and domains to improve th
Externí odkaz:
http://arxiv.org/abs/2310.06124