Zobrazeno 1 - 10
of 742
pro vyhledávání: '"Mazzara, P"'
The classification of hyperspectral images (HSI) is a challenging task due to the high spectral dimensionality and limited labeled data typically available for training. In this study, we propose a novel multi-stage active transfer learning (ATL) fra
Externí odkaz:
http://arxiv.org/abs/2411.18115
Autor:
Salem, Hamza, Mazzara, Manuel
The rapid expansion of the non-fungible token (NFT) market has catalyzed new opportunities for artists, collectors, and investors, yet it has also unveiled critical challenges related to the storage and distribution of associated metadata. This paper
Externí odkaz:
http://arxiv.org/abs/2408.13281
Autor:
Ahmad, Muhammad, Butt, Muhammad Hassaan Farooq, Khan, Adil Mehmood, Mazzara, Manuel, Distefano, Salvatore, Usama, Muhammad, Roy, Swalpa Kumar, Chanussot, Jocelyn, Hong, Danfeng
Recent advancements in transformers, specifically self-attention mechanisms, have significantly improved hyperspectral image (HSI) classification. However, these models often suffer from inefficiencies, as their computational complexity scales quadra
Externí odkaz:
http://arxiv.org/abs/2408.01372
Hyperspectral Imaging (HSI) has proven to be a powerful tool for capturing detailed spectral and spatial information across diverse applications. Despite the advancements in Deep Learning (DL) and Transformer architectures for HSI classification, cha
Externí odkaz:
http://arxiv.org/abs/2408.01231
Autor:
Ahmad, Muhammad, Butt, Muhammad Hassaan Farooq, Usama, Muhammad, Altuwaijri, Hamad Ahmed, Mazzara, Manuel, Distefano, Salvatore
Spatial-Spectral Mamba (SSM) improves computational efficiency and captures long-range dependencies, addressing Transformer limitations. However, traditional Mamba models overlook rich spectral information in HSIs and struggle with high dimensionalit
Externí odkaz:
http://arxiv.org/abs/2408.01224
This paper addresses the challenge of learning to recite the Quran for non-Arabic speakers. We explore the possibility of crowdsourcing a carefully annotated Quranic dataset, on top of which AI models can be built to simplify the learning process. In
Externí odkaz:
http://arxiv.org/abs/2405.02675
3D Swin Transformer (3D-ST) known for its hierarchical attention and window-based processing, excels in capturing intricate spatial relationships within images. Spatial-spectral Transformer (SST), meanwhile, specializes in modeling long-range depende
Externí odkaz:
http://arxiv.org/abs/2405.01095
Autor:
Ahmad, Muhammad, Distifano, Salvatore, Khan, Adil Mehmood, Mazzara, Manuel, Li, Chenyu, Li, Hao, Aryal, Jagannath, Ding, Yao, Vivone, Gemine, Hong, Danfeng
Hyperspectral Image Classification (HSC) presents significant challenges owing to the high dimensionality and intricate nature of Hyperspectral (HS) data. While traditional Machine Learning (TML) approaches have demonstrated effectiveness, they often
Externí odkaz:
http://arxiv.org/abs/2404.14955
The traditional Transformer model encounters challenges with variable-length input sequences, particularly in Hyperspectral Image Classification (HSIC), leading to efficiency and scalability concerns. To overcome this, we propose a pyramid-based hier
Externí odkaz:
http://arxiv.org/abs/2404.14945
Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art (SOTA) models. When training, validation, and test sets overlap or share data, it introduces a bias that inflates performance metrics and prevents accurate assessm
Externí odkaz:
http://arxiv.org/abs/2404.14944