Attention attention everywhere: Monocular depth prediction with skip attention

A Agarwal, C Arora - Proceedings of the IEEE/CVF Winter …, 2023‏ - openaccess.thecvf.com
Abstract Monocular Depth Estimation (MDE) aims to predict pixel-wise depth given a single
RGB image. For both, the convolutional as well as the recent attention-based models …

ST-unet: Swin transformer boosted U-net with cross-layer feature enhancement for medical image segmentation

J Zhang, Q Qin, Q Ye, T Ruan - Computers in Biology and Medicine, 2023‏ - Elsevier
Medical image segmentation is an essential task in clinical diagnosis and case analysis.
Most of the existing methods are based on U-shaped convolutional neural networks (CNNs) …

Rs-net: Residual Sharp U-Net architecture for pavement crack segmentation and severity assessment

L Ali, H AlJassmi, M Swavaf, W Khan, F Alnajjar - Journal of Big Data, 2024‏ - Springer
U-net, a fully convolutional network-based image segmentation method, has demonstrated
widespread adaptability in the crack segmentation task. The combination of the semantically …

Augmenting DenseNet: Leveraging Multi-Scale Skip Connections for Effective Early-Layer Information Incorporation

SA Samad, J Gitanjali - IEEE Access, 2024‏ - ieeexplore.ieee.org
The proliferation of Convolutional Neural Network-based applications in recent years has
necessitated the development of effective strategies for information and gradient flow within …

Fusing Multispectral and LiDAR Data for CNN-Based Semantic Segmentation in Semi-Arid Mediterranean Environments: Land Cover Classification and Analysis

A Chroni, C Vasilakos, M Christaki… - Remote …, 2024‏ - search.proquest.com
Spectral confusion among land cover classes is quite common, let alone in a complex and
heterogenous system like the semi-arid Mediterranean environment; thus, employing new …

DwinFormer: Dual window transformers for end-to-end monocular depth estimation

MA Rahman, SA Fattah - IEEE Sensors Journal, 2023‏ - ieeexplore.ieee.org
Depth estimation using monocular vision sensors is crucial in computer vision, with diverse
applications ranging from autonomous driving to robot motion. Conventional methods suffer …

Leveraging U-Net and selective feature extraction for land cover classification using remote sensing imagery

LT Ramos, AD Sappa - Scientific Reports, 2025‏ - nature.com
In this study, we explore an enhancement to the U-Net architecture by integrating SK-
ResNeXt as the encoder for Land Cover Classification (LCC) tasks using Multispectral …

Nested DWT–Based CNN Architecture for Monocular Depth Estimation

S Paul, D Mishra, SK Marimuthu - Sensors, 2023‏ - mdpi.com
Applications such as medical diagnosis, navigation, robotics, etc., require 3D images.
Recently, deep learning networks have been extensively applied to estimate depth. Depth …

RWKV-UNet: Improving UNet with Long-Range Cooperation for Effective Medical Image Segmentation

J Jiang, J Zhang, W Liu, M Gao, X Hu, X Yan… - arxiv preprint arxiv …, 2025‏ - arxiv.org
In recent years, there have been significant advancements in deep learning for medical
image analysis, especially with convolutional neural networks (CNNs) and transformer …

BCNet: integrating UNet and transformer for blood cell segmentation

Y Jiang, S Wang, M Yao, Q **ao, Y Li, H Bai… - Signal, Image and Video …, 2025‏ - Springer
Automatic segmentation of blood cells is crucial in medical diagnosis and research,
significantly improving the accuracy and efficiency of diagnosing blood disorders. Traditional …