Search Results - "Asymmetric encoder–decoder architecture"

Ghost-UNet: An Asymmetric Encoder-Decoder Architecture for Semantic Segmentation From Scratch

Authors: Iman Abaspur Kazerouni Gerard Dooly Daniel Toal et al.

Contributors: Iman Abaspur Kazerouni Gerard Dooly Daniel Toal et al.

Source: IEEE Access, Vol 9, Pp 97457-97465 (2021)
IEEE Access

Subject Terms: mobile robots, 11. Sustainability, Mobile robots, 0202 electrical engineering, electronic engineering, information engineering, deep learning, Electrical engineering. Electronics. Nuclear engineering, scene understanding, 02 engineering and technology, semantic segmentation, TK1-9971

File Description: application/pdf

Access URL: https://ieeexplore.ieee.org/ielx7/6287639/6514899/09475058.pdf
https://doaj.org/article/3d06dd476b5e4558afe77b5302df6d18

Ghost-UNet: an asymmetric encoder-decoder architecture for semantic segmentation From scratch

Subject Terms: mobile robots, deep learning, scene understanding, semantic segmentation

Access URL: https://figshare.com/articles/Ghost-UNet_an_asymmetric_encoder-decoder_architecture_for_semantic_segmentation_From_scratch/19813132/1
https://hdl.handle.net/10344/10597

Hyperspectral Image Denoising via Quasi-Recursive Spectral Attention and Cross-Layer Feature Fusion.

Authors: Xiao, Yanhua Zhou, Huayan Li, Wenfeng et al.

Source: Sensors (14248220); Nov2025, Vol. 25 Issue 22, p6955, 18p

Subject Terms: IMAGE denoising, FEATURE extraction, SIGNAL denoising, ARTIFICIAL neural networks, HYPERSPECTRAL imaging systems

基于多尺度掩码自编码的自监督点云场景流估计. (Chinese)

Alternate Title: Self-supervised scene flow estimation based on multiscale masked autoencoders. (English)

Authors: 项学智 王 茜 王 路 et al.

Source: Experimental Technology & Management; Sep2025, Vol. 42 Issue 9, p27-33, 7p

Subject Terms: POINT cloud, AUTONOMOUS vehicles, GEOMETRIC modeling, FEATURE extraction, MOTION estimation (Signal processing), MACHINE learning

FS-MSFormer: Image Dehazing Based on Frequency Selection and Multi-Branch Efficient Transformer.

Authors: Tang, Chunming Wang, Yu

Source: Computers, Materials & Continua; 2025, Vol. 83 Issue 3, p5115-5128, 14p

Subject Terms: TRANSFORMER models, CONVOLUTIONAL neural networks, FEATURE extraction, ENCODING

Lightweight single-head attention mechanism-driven diffusion model for hyperspectral image classification.

Authors: Fang, Qizhi Zhao, Yubo Wang, Jingang et al.

Source: Journal of Supercomputing. Jul2025, Vol. 81 Issue 10, p1-33. 33p.

MeshMask: Physics-Based Simulations with Masked Graph Neural Networks

Authors: Garnier, Paul Lannelongue, Vincent Viquerat, Jonathan et al.

Index Terms: Computer Science - Machine Learning, Physics - Fluid Dynamics, text

URL: http://arxiv.org/abs/2501.08738

An Information Entropy Masked Vision Transformer (IEM-ViT) Model for Recognition of Tea Diseases.

Authors: Zhang, Jiahong Guo, Honglie Guo, Jin et al.

Source: Agronomy; Apr2023, Vol. 13 Issue 4, p1156, 16p

Subject Terms: ENTROPY (Information theory), IMAGE recognition (Computer vision), TEA, DATA augmentation, RECOGNITION (Psychology)

CoMiX: Cross-Modal Fusion with Deformable Convolutions for HSI-X Semantic Segmentation

Authors: Zhang, Xuming Gu, Xingfa Tian, Qingjiu et al.

Index Terms: Computer Science - Computer Vision and Pattern Recognition, text

URL: http://arxiv.org/abs/2411.09023

FRNet: Factorized and Regular Blocks Network for Semantic Segmentation in Road Scene.

Authors: Lu, Mengxu Chen, Zhenxue Wu, Q. M. Jonathan et al.

Source: IEEE Transactions on Intelligent Transportation Systems; Apr2022, Vol. 23 Issue 4, p3522-3530, 9p

LAANet: lightweight attention-guided asymmetric network for real-time semantic segmentation.

Authors: Zhang, Xiuling Du, Bingce Wu, Ziyun et al.

Source: Neural Computing & Applications; Mar2022, Vol. 34 Issue 5, p3573-3587, 15p

Subject Terms: AUTONOMOUS vehicles, AUTONOMOUS robots, PYRAMIDS

Lightweight and efficient asymmetric network design for real-time semantic segmentation.

Authors: Zhang, Xiu-Ling Du, Bing-Ce Luo, Zhao-Ci et al.

Source: Applied Intelligence; Jan2022, Vol. 52 Issue 1, p564-579, 16p

Subject Terms: DRONE photography, AERIAL photography, FEATURE selection, AUTONOMOUS vehicles, BOTTLENECKS (Manufacturing)

A Comprehensive Review of Multimodal Visual Representation Learning: Tracing the Evolution from CNNs to Transformers and Beyond.

Authors: Zhang, Dong Wong, W. K. Chew, I. M.

Source: International Journal of Multimedia Information Retrieval; Dec2025, Vol. 14 Issue 4, p1-30, 30p

DLCPD-25: A Large-Scale and Diverse Dataset for Crop Disease and Pest Recognition.

Authors: Zhang, Heng-Wei Wang, Rui-Feng Wang, Zhengle et al.

Source: Sensors (14248220); Nov2025, Vol. 25 Issue 22, p7098, 27p

Subject Terms: PLANT diseases, AGRICULTURAL pests, ACQUISITION of data, FOOD security, AGRICULTURE, DEEP learning, AUTOENCODERS, IMAGE recognition (Computer vision)

Speech Separation Using Advanced Deep Neural Network Methods: A Recent Survey.

Authors: Wang, Zeng Luo, Zhongqiang

Source: Big Data & Cognitive Computing; Nov2025, Vol. 9 Issue 11, p289, 37p

Subject Terms: ARTIFICIAL neural networks, SIGNAL separation, LOSS functions (Statistics), TECHNOLOGICAL innovations, ACOUSTIC signal processing, SOFTWARE architecture, SCIENTIFIC method

Visual residual aggregation network for visual-language prompt tuning.

Authors: Yu, Yunqian Guo, Feng Tian, Xianlong et al.

Source: Applied Intelligence; Oct2025, Vol. 55 Issue 15, p1-19, 19p

Biology-driven insights into the power of single-cell foundation models.

Authors: Wu, Jialu Ye, Qing Wang, Yilin et al.

Source: Genome Biology; 10/3/2025, Vol. 26 Issue 1, p1-39, 39p

Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems

Authors: Su, Zhenpeng Wu, Xing Zhou, Wei et al.

Index Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence, text

URL: http://arxiv.org/abs/2306.04357

SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrieval

Authors: Li, Haitao Ai, Qingyao Chen, Jia et al.

Index Terms: Computer Science - Information Retrieval, Computer Science - Computation and Language, text

URL: http://arxiv.org/abs/2304.11370

Fast Training of Diffusion Models with Masked Transformers

Authors: Zheng, Hongkai Nie, Weili Vahdat, Arash et al.

Index Terms: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, text

URL: http://arxiv.org/abs/2306.09305