Zobrazeno 1 - 10
of 373
pro vyhledávání: '"A. Manzuri"'
Spuriosity Rankings for Free: A Simple Framework for Last Layer Retraining Based on Object Detection
Autor:
Azizmalayeri, Mohammad, Abbasi, Reza, rezaie, Amir Hosein Haji Mohammad, Zohrabi, Reihaneh, Amiri, Mahdi, Manzuri, Mohammad Taghi, Rohban, Mohammad Hossein
Deep neural networks have exhibited remarkable performance in various domains. However, the reliance of these models on spurious features has raised concerns about their reliability. A promising solution to this problem is last-layer retraining, whic
Externí odkaz:
http://arxiv.org/abs/2311.00079
Autor:
Salmani, Mahdi, Farashah, Alireza Dehghanpour, Azizmalayeri, Mohammad, Amiri, Mahdi, Eslami, Navid, Manzuri, Mohammad Taghi, Rohban, Mohammad Hossein
Despite the remarkable success achieved by deep learning algorithms in various domains, such as computer vision, they remain vulnerable to adversarial perturbations. Adversarial Training (AT) stands out as one of the most effective solutions to addre
Externí odkaz:
http://arxiv.org/abs/2310.18975
Autor:
Moakhar, Arshia Soltani, Azizmalayeri, Mohammad, Mirzaei, Hossein, Manzuri, Mohammad Taghi, Rohban, Mohammad Hossein
Despite considerable theoretical progress in the training of neural networks viewed as a multi-agent system of neurons, particularly concerning biological plausibility and decentralized training, their applicability to real-world problems remains lim
Externí odkaz:
http://arxiv.org/abs/2310.09952
Autor:
Azizmalayeri, Mohammad, Zarei, Arman, Isavand, Alireza, Manzuri, Mohammad Taghi, Rohban, Mohammad Hossein
Current machine learning models achieve super-human performance in many real-world applications. Still, they are susceptible against imperceptible adversarial perturbations. The most effective solution for this problem is adversarial training that tr
Externí odkaz:
http://arxiv.org/abs/2301.10454
Autor:
Azizmalayeri, Mohammad, Moakhar, Arshia Soltani, Zarei, Arman, Zohrabi, Reihaneh, Manzuri, Mohammad Taghi, Rohban, Mohammad Hossein
Out-of-distribution (OOD) detection has recently gained substantial attention due to the importance of identifying out-of-domain samples in reliability and safety. Although OOD detection methods have advanced by a great deal, they are still susceptib
Externí odkaz:
http://arxiv.org/abs/2209.15246
Modern neural networks are powerful predictive models. However, when it comes to recognizing that they may be wrong about their predictions, they perform poorly. For example, for one of the most common activation functions, the ReLU and its variants,
Externí odkaz:
http://arxiv.org/abs/2109.02137
Autor:
Yousefi, Sahar, Sokooti, Hessam, Elmahdy, Mohamed S., Lips, Irene M., Shalmani, Mohammad T. Manzuri, Zinkstok, Roel T., Dankers, Frank J. W. M., Staring, Marius
Manual or automatic delineation of the esophageal tumor in CT images is known to be very challenging. This is due to the low contrast between the tumor and adjacent tissues, the anatomical variation of the esophagus, as well as the occasional presenc
Externí odkaz:
http://arxiv.org/abs/2012.03242
The success of deep neural networks (DNN) in machine perception applications such as image classification and speech recognition comes at the cost of high computation and storage complexity. Inference of uncompressed large scale DNN models can only r
Externí odkaz:
http://arxiv.org/abs/2007.01793
Publikováno v:
In Engineering Applications of Artificial Intelligence February 2023 118
Generative dynamic texture models (GDTMs) are widely used for dynamic texture (DT) segmentation in the video sequences. GDTMs represent DTs as a set of linear dynamical systems (LDSs). A major limitation of these models concerns the automatic selecti
Externí odkaz:
http://arxiv.org/abs/1901.03968