Zobrazeno 1 - 10
of 521
pro vyhledávání: '"Rohban A"'
Text-to-image (T2I) generative models, such as Stable Diffusion and DALL-E, have shown remarkable proficiency in producing high-quality, realistic, and natural images from textual descriptions. However, these models sometimes fail to accurately captu
Externí odkaz:
http://arxiv.org/abs/2410.22775
Autor:
Marioriyad, Arash, Banayeeanzade, Mohammadali, Abbasi, Reza, Rohban, Mohammad Hossein, Baghshah, Mahdieh Soleymani
Text-to-image diffusion models, such as Stable Diffusion and DALL-E, are capable of generating high-quality, diverse, and realistic images from textual prompts. However, they sometimes struggle to accurately depict specific entities described in prom
Externí odkaz:
http://arxiv.org/abs/2410.20972
Autor:
Ghaznavi, Mahdi, Asadollahzadeh, Hesam, Noohdani, Fahimeh Hosseini, Tabar, Soroush Vafaie, Hasani, Hosein, Alvanagh, Taha Akbari, Rohban, Mohammad Hossein, Baghshah, Mahdieh Soleymani
Classifiers trained with Empirical Risk Minimization (ERM) tend to rely on attributes that have high spurious correlation with the target. This can degrade the performance on underrepresented (or 'minority') groups that lack these attributes, posing
Externí odkaz:
http://arxiv.org/abs/2410.05345
Autor:
Afshar, Pardis, Hashembeiki, Sajjad, Khani, Pouya, Fatemizadeh, Emad, Rohban, Mohammad Hossein
Histopathological image analysis is crucial for accurate cancer diagnosis and treatment planning. While deep learning models, especially convolutional neural networks, have advanced this field, their "black-box" nature raises concerns about interpret
Externí odkaz:
http://arxiv.org/abs/2408.16395
Autor:
Mirzaei, Hossein, Nafez, Mojtaba, Jafari, Mohammad, Soltani, Mohammad Bagher, Azizmalayeri, Mohammad, Habibi, Jafar, Sabokrou, Mohammad, Rohban, Mohammad Hossein
Novelty detection is a critical task for deploying machine learning models in the open world. A crucial property of novelty detection methods is universality, which can be interpreted as generalization across various distributions of training or test
Externí odkaz:
http://arxiv.org/abs/2408.10798
Autor:
Jafarinia, Hossein, Alipanah, Alireza, Hamdi, Danial, Razavi, Saeed, Mirzaie, Nahal, Rohban, Mohammad Hossein
Whole Slide Image (WSI) classification with multiple instance learning (MIL) in digital pathology faces significant computational challenges. Current methods mostly rely on extensive self-supervised learning (SSL) for satisfactory performance, requir
Externí odkaz:
http://arxiv.org/abs/2408.08258
Autor:
Abdollahi, Ali, Ghaznavi, Mahdi, Nejad, Mohammad Reza Karimi, Oriyad, Arash Mari, Abbasi, Reza, Salesi, Ali, Behjati, Melika, Rohban, Mohammad Hossein, Baghshah, Mahdieh Soleymani
Publikováno v:
Volume 392 of ECAI 2024, Pages 729 - 736
Vision-language models (VLMs) are intensively used in many downstream tasks, including those requiring assessments of individuals appearing in the images. While VLMs perform well in simple single-person scenarios, in real-world applications, we often
Externí odkaz:
http://arxiv.org/abs/2407.21001
CLIP models have recently shown to exhibit Out of Distribution (OoD) generalization capabilities. However, Compositional Out of Distribution (C-OoD) generalization, which is a crucial aspect of a model's ability to understand unseen compositions of k
Externí odkaz:
http://arxiv.org/abs/2407.05897
Autor:
Ghahroodi, Omid, Nouri, Marzia, Sanian, Mohammad Vali, Sahebi, Alireza, Dastgheib, Doratossadat, Asgari, Ehsaneddin, Baghshah, Mahdieh Soleymani, Rohban, Mohammad Hossein
Evaluating Large Language Models (LLMs) is challenging due to their generative nature, necessitating precise evaluation methodologies. Additionally, non-English LLM evaluation lags behind English, resulting in the absence or weakness of LLMs for many
Externí odkaz:
http://arxiv.org/abs/2404.06644
Vision-language models, such as CLIP, have shown promising Out-of-Distribution (OoD) generalization under various types of distribution shifts. Recent studies attempted to investigate the leading cause of this capability. In this work, we follow the
Externí odkaz:
http://arxiv.org/abs/2403.18525