Výsledky vyhľadávania - encoder‐decoder architecture variants*

An Empirical Analysis of Encoder-Decoder (U-Net) Variants for Medical Image Segmentation

Autori: Jackson Kamiri Geoffrey Mariga Wambugu Aaron Mogeni Oirere

Zdroj: International Journal of Scientific Research in Computer Science and Engineering. 13:26-31

Comparative analysis of u-net architectures and variants for hand gesture segmentation in parkinson’s patients

Autori: Avadhoot Ramgonda Telepatil Jayashree Sathyanarayana Vaddin

Zdroj: International Journal of Informatics and Communication Technology (IJ-ICT). 14:972

CovSegNet: A Multi Encoder-Decoder Architecture for Improved Lesion Segmentation of COVID-19 Chest CT Scans.

Autori: Mahmud, Tanvir Rahman, Md Fattah, Shaikh a ďalší

Zdroj: IEEE Transactions on Artificial Intelligence. 2(3)

Predmety: Artificial intelligence (AI), biomedical imaging, computer aided analysis, image segmentation, neural networks

Popis súboru: application/pdf

Prístupová URL adresa: https://escholarship.org/uc/item/51g6b93g
https://escholarship.org/content/qt51g6b93g/qt51g6b93g.pdf

Investigating U-Net variants for satellite image object detection: Towards an ensemble method and performance evaluation.

Autori: Malik, Sunesh Nandal, Priyanka Pahal, Sudesh a ďalší

Zdroj: Evolving Systems; Sep2025, Vol. 16 Issue 3, p1-20, 20p

TlED-Net: optimizing semantic segmentation via triple-loop encoder-decoder architecture with dense skip connections.

Autori: Wei, Yuanhong Wang, Yuefei

Zdroj: Visual Computer; Oct2025, Vol. 41 Issue 13, p10691-10722, 32p

Predmety: IMAGE segmentation, FEATURE extraction, COMPUTER-assisted image analysis (Medicine), ARTIFICIAL neural networks

Efficient segmentation and classification of the tumor using improved encoder-decoder architecture in brain MRI images

Autori: Ingle, Archana Roja, Mani Sankhe, Manoj a ďalší

Zdroj: International journal of electrical and computer engineering systems
Volume 13
Issue 8

Predmety: Brain tumor Segmentation, Deep Learning, UNet, Convolutional Neural Network, Transfer Learning, ResNext, CNN, ResNet

Popis súboru: application/pdf

BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder Architecture

Autori: Xiang, Tiange Zhang, Chaoyi Liu, Dongnan a ďalší

Témy: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Image and Video Processing, text

URL: http://arxiv.org/abs/2007.00243

Enhanced U-Net architectures for accurate room impulse response generation via differential-phase learning.

Autori: Martin-Salinas, Ignacio Piñero, Gema Belloch, Jose A. a ďalší

Zdroj: EURASIP Journal on Audio Speech & Music Processing; 11/17/2025, Vol. 2025 Issue 1, p1-15, 15p

Predmety: PHASE estimation (Electronics), DEEP learning, LOSS functions (Statistics), ARCHITECTURAL acoustics, LATENT variables

Semantic road segmentation using encoder-decoder architectures.

Autori: Latsaheb, Burhanuddin Sharma, Sanjeev Hasija, Sanskar

Zdroj: Multimedia Tools & Applications; Mar2025, Vol. 84 Issue 9, p5961-5983, 23p

Predmety: COGNITIVE psychology, DEEP learning, ARTIFICIAL intelligence, IMAGE processing, INFORMATION architecture

Defending Deep Learning-Based Raw Malware Detectors Against Adversarial Attacks: A Sequence Modeling Approach.

Autori: Ebrahimi, Reza Hu, James Lee Zhang, Ning a ďalší

Zdroj: Journal of Management Information Systems; 2025, Vol. 42 Issue 4, p1118-1148, 31p

Predmety: DEEP learning, MALWARE, RECURRENT neural networks, INTERNET security, GENERATIVE artificial intelligence, CYBERTERRORISM

CovSegNet: A Multi Encoder-Decoder Architecture for Improved Lesion Segmentation of COVID-19 Chest CT Scans

Autori: Mahmud, Tanvir Rahman, Md Awsafur Fattah, Shaikh Anowarul a ďalší

Témy: Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, text

URL: http://arxiv.org/abs/2012.01473

BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder Architecture

Autori: Yang Song Tiange Xiang Chaoyi Zhang a ďalší

Zdroj: Lecture Notes in Computer Science ISBN: 9783030597092

Predmety: FOS: Computer and information sciences, Computer Science - Machine Learning, 03 medical and health sciences, 0302 clinical medicine, Computer Vision and Pattern Recognition (cs.CV), Image and Video Processing (eess.IV), Computer Science - Computer Vision and Pattern Recognition, 0202 electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering, 02 engineering and technology, Electrical Engineering and Systems Science - Image and Video Processing, Machine Learning (cs.LG)

Prístupová URL adresa: http://arxiv.org/pdf/2007.00243
http://arxiv.org/abs/2007.00243
https://link.springer.com/chapter/10.1007/978-3-030-59710-8_8
https://dblp.uni-trier.de/db/journals/corr/corr2007.html#abs-2007-00243
https://rd.springer.com/chapter/10.1007/978-3-030-59710-8_8

Comparative Analysis of Deep Learning Architectures for Macular Hole Segmentation in OCT Images: A Performance Evaluation of U-Net Variants.

Autori: Herath, H. M. S. S. Yasakethu, S. L. P. Madusanka, Nuwan a ďalší

Zdroj: Journal of Imaging; Feb2025, Vol. 11 Issue 2, p53, 18p

Predmety: CONVOLUTIONAL neural networks, OPTICAL coherence tomography, TRANSFORMER models, IMAGE segmentation, CLINICAL medicine, DEEP learning

Transformer architectures for computer vision: A comprehensive review and future research directions.

Autori: Ugile, Tukaram Uke, Nilesh

Zdroj: EPJ Web of Conferences; 11/20/2025, Vol. 341, p1-13, 13p

Predmety: TRANSFORMER models, COMPUTER vision, EDGE computing, OBJECT recognition (Computer vision)

FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration

Autori: Xu, Kai-Tuo Xie, Feng-Long Tang, Xu a ďalší

Témy: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Sound, text

URL: http://arxiv.org/abs/2501.14350

Efficient compression of encoder-decoder models for semantic segmentation using the separation index.

Autori: Jamshidi, Movahed Kalhor, Ahmad Vahabie, Abdol-Hossein

Zdroj: Scientific Reports; 7/9/2025, Vol. 15 Issue 1, p1-19, 19p

Predmety: IMAGE segmentation, MATHEMATICAL optimization

An open-source family of large encoder-decoder foundation models for chemistry.

Autori: Soares, Eduardo Vital Brazil, Emilio Shirasuna, Victor a ďalší

Zdroj: Communications Chemistry; 7/1/2025, Vol. 8 Issue 1, p1-9, 9p

Predmety: LANGUAGE models, NATURAL language processing, CHEMICAL models, DATA quality, SMILING

A dual attention and cross layer fusion network with a hybrid CNN and transformer architecture for medical image segmentation.

Autori: Chen, Jiahong Liang, Zhengyou Lu, Xiangyan

Zdroj: Scientific Reports; 10/13/2025, Vol. 15 Issue 1, p1-17, 17p

Predmety: IMAGE segmentation, ATTENTION, CONVOLUTIONAL neural networks, TRANSFORMER models, FEATURE selection

Compare Encoder-Decoder, Encoder-Only, and Decoder-Only Architectures for Text Generation on Low-Resource Datasets

Autori: Yao-Chung Fan Fang-Yie Leu Pei-Xuan Cai

Zdroj: Lecture Notes in Networks and Systems ISBN: 9783030900717

Prístupová URL adresa: https://link.springer.com/chapter/10.1007/978-3-030-90072-4_23

Advanced Implementation of a Multilevel Model for Text Summarization in Kazakh Using Pretrained Models.

Autori: Oralbekova, Dina Mamyrbayev, Orken Othman, Mohamed a ďalší

Zdroj: Engineering, Technology & Applied Science Research; Oct2025, Vol. 15 Issue 5, p26711-26721, 11p

Predmety: TEXT summarization, TRANSFORMER models, SOFTWARE architecture