17 papers · ranked by Valyu relevance
Abdelrahman Yehia, Naser El-Sheimy, Ashraf Helmy, Ibrahim Sh. Sanad + 2 more
Synthetic Aperture Radar (SAR) ship detection remains challenging due to background clutter, target sparsity, and fragmented or partially occluded ships, particularly at small scales. To address these issues, we propose the Deformable Recurrent Criss-Cross Attention Network ( $\text{DRC}2$-Net), a lightweight and…
Jack T. Beerman, Shobhan Roy, H. S. Udaykumar, Stephen S. Baek
Physics-aware deep learning (PADL) enables rapid prediction of complex physical systems, yet current convolutional neural network (CNN) architectures struggle with highly nonlinear flows. While scaling model size addresses complexity in broader AI, this approach yields diminishing returns for physics modeling. Drawing…
Chengkun Sun, Jinqian Pan, Renjie Liang, Zhengkang Fan + 3 more
In medical image segmentation, particularly in UNet-like architectures, upsampling is primarily used to transform smaller feature maps into larger ones, enabling feature fusion between encoder and decoder features and supporting multi-scale prediction. Conventional upsampling methods, such as transposed convolution and…
Dario Morle, Reid Zaffino
Dynamic sampling mechanisms in deep learning architectures have demonstrated utility across many computer vision models, though the theoretical analysis of these structures has not yet been unified. In this paper we connect the various dynamic sampling methods by developing and analyzing a novel operator which…
Lingfei He, Hongping Hu, Rong Cheng, Xiaohui Zhang
Breast cancer is a highly heterogeneous malignant tumor, and its accurate classification is of great significance for clinical diagnosis and treatment decision-making. In recent years, convolutional neural networks and Transformer have been widely used in pathological image analysis of breast cancer. Though the former…
Huilin Li, Chengyang Zhang, Shaowei Ye
Road potholes present a significant challenge to urban traffic safety and infrastructure maintenance. Traditional manual inspection methods fail to meet the demands for real-time performance and high accuracy. In this study, we propose ECC-YOLO, a lightweight object detection model based on YOLOv11n, specifically…
Haoxiang Peng, Chengrong Wu, Yuhao Du, Hui Liu
Title: Summary Meteorological drought prediction is critical for early warning and climate-risk management; yet, modeling regional drought evolution across multi-timescale remains challenging. Here, we propose DCSwinLSTM, a feature-fusion framework that combines deformable convolution for boundary-sensitive spatial…
Cuixin Yang, Rongkang Dong, Kin-Man LAM, Yuhang Zhang + 1 more
As augmented reality and virtual reality applications gain popularity, image processing for OmniDirectional Images (ODIs) has attracted increasing attention. OmniDirectional Image Super-Resolution (ODISR) is a promising technique for enhancing the visual quality of ODIs. Before performing superresolution, ODIs are…
Dongyan Zhang, Jincan Zhang, Wenna Chen, Ganqin Du
Background Convolutional neural networks (CNNs) have achieved remarkable success in medical image analysis, including Alzheimer’s disease (AD) classification. However, conventional convolution operations rely on fixed sampling patterns, and most existing attention mechanisms primarily focus on feature responses while…
Lei Li, Weili Wu, Zhong Li, Jun Wu
Aiming at the problem that fault characteristics cannot be effectively expressed due to the low pixel proportion of the hot spot target and background interference when detecting hot spot faults in complex environments, a photovoltaic module hot spot fault detection method integrating U-Net and YOLOv8 is proposed.…
Yifan Zhou, Takehiko Ohkawa, Zhou, Guwenxiao + 4 more
Modeling daily hand interactions often struggles with severe occlusions, such as when two hands overlap, which highlights the need for robust feature learning in 3D hand pose estimation (HPE). To handle such occluded hand images, it is vital to effectively learn the relationship between local image features (e.g., for…
Jiarui Xue, Dongjian Yang, Ye Sun, Gang Liu
—In real-world scenarios of image recognition, there exists substantial noise interference. Existing works primarily focus on methods such as adjusting networks or training strategies to address noisy image recognition, and the antinoise performance has reached a bottleneck. However, little is known about the…
Zhongming Liu, Bingbing Jiang, Guangxin Wan, Xiang Zou
Steel surface defect segmentation is critical for industrial quality inspection, yet existing methods struggle with elongated, anisotropic defects such as cracks and scratches due to the isotropic receptive fields of standard convolutions and rigid sampling grids that cannot adapt to irregular defect boundaries. To…
Zhenbang Zhang, Jingtong Feng, Hongjia Li, Haythem El-Messiry + 3 more
After LRR, two local deformation fields $Φ_{1,0}$ and $Φ_{1,1}$, are generated. These fields are then used to warp the segmented image regions ${I_{1,0},I_{1,1}}$ and corresponding masks ${M_{1,0},M_{1,1}}$. Finally, a pixel-wise weighted fusion is performed to reconstruct the unfolded image $I_{1}^$…
Kishore Kumar Tarafdar
Deep learning models are widely used to process multidimensional signals such as time series, images, and volumetric medical images, but their learned representations often lack explicit signal structure and are difficult to inspect. This thesis develops model-based, signal-theoretic learning systems guided by data and…
Peter Kirchweger, Lev Melnikovsky, Shahar Seifer, Michael Elbaum
Cryo-electron tomography is an expanding technology for the study of macromolecules, viruses, and cells. It is often applied to specimens that are too large or heterogeneous for methods based on 2D image averaging such as single particle analysis, e.g., intracellular membranes or organelles. Current practice records a…
Haohong Gan, Shiyi Peng, Hailian Hu, Xuan You + 4 more
The resolving power of optical microscopy is fundamentally constrained by the diffraction of light, limiting our ability to visualize subcellular structures. Computational methods, particularly deconvolution, can restore blurred images but critically depend on an accurate point spread function (PSF), whose estimation…