22 papers · ranked by Valyu relevance
Jifeng Dai, Haozhi Qi, Yuwen Xiong, Yi Li + 3 more
'Yichen Wei'] Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in their building modules. In this work, we introduce two new modules to enhance the transformation modeling capability of CNNs, namely, deformable convolution and…
Effat Sahragard, Hassan Farsi, Sajad Mohamadzadeh, Antonio Agudo
This paper presents a novel method for improving semantic segmentation performance in computer vision tasks. Our approach utilizes an enhanced UNet architecture that leverages an improved ResNet50 backbone. We replace the last layer of ResNet50 with deformable convolution to enhance feature representation.…
Jun Xiang, Ruru Pan, Weidong Gao, Kelvin K.L. Wong
The traditional manual defect detection method has low efficiency and is time-consuming and laborious. To address this issue, this paper proposed an automatic detection framework for fabric defect detection, which consists of a hardware system and detection algorithm. For the efficient and high-quality acquisition of…
Chengming Rao, Zunhao Hu, QiMing Zhao, Min Shan + 2 more
One of the main challenges encountered in visual object detection is the multi-scale issue. Many approaches have been proposed to tackle this issue. In this article, we propose a novel neck that can perform effective fusion of multi-scale features for a single-stage object detector. This neck, named the deformable…
Jiarui Feng, Shenghui Zhang, Zhaoyu Zhai, Hongfeng Yu + 1 more
Asian soybean rust (ASR) is one of the major diseases that causes serious yield loss worldwide, even up to 80%. Early and accurate detection of ASR is critical to reduce economic losses. Hyperspectral imaging, combined with deep learning, has already been proved as a powerful tool to detect crop diseases. However…
Zhu, Lexuan, Li, Yuxuan + 2 more
- We propose a plug-and-play deformable convolution with globally learned relative offsets, a module well suited to handle complex zigzag edge features. Compared with other existing deformable convolution, the proposed convolution has the following different characteristics: - Offsets are learned using multi-head…
Xubo Li, Wenqing Wang, Lihua Sun, Bin Hu + 2 more
'Jincheng Zhang'] When performed by a person, aero-engine borescope inspection is easily influenced by individual experience and human factors that can lead to incorrect maintenance decisions, potentially resulting in serious disasters, as well as low efficiency. To address the absolute requirements of flight safety…
Miao Zou, Xi Li, Quan Yuan, Tao Xiong + 5 more
'Zhenhua Xiao' 'Chaoran Cui' 'Xiaohui Han'] In this article, we propose an effective grasp detection network based on an improved deformable convolution and spatial feature center mechanism (DCSFC-Grasp) to precisely grasp unidentified objects. DCSFC-Grasp includes three key procedures as follows. First, improved…
Qijing Huang, Dequan Wang, Yizhao Gao, Yaohui Cai + 4 more
'Bichen Wu' 'Kurt Keutzer' 'John Wawrzynek'] FPGAs provide a flexible and efficient platform to accelerate rapidly-changing algorithms for computer vision. The majority of existing work focuses on accelerating image classification, while other fundamental vision problems, including object detection and instance…
Xin Zhang, Yingze Song, Tingting Song, Degang Yang + 3 more
'Jie Zhou' 'Liming Zhang'] Neural networks based on convolutional operations have achieved remarkable results in the field of deep learning, but there are two inherent flaws in standard convolutional operations. On the one hand, the convolution operation is confined to a local window, so it cannot capture information…
Xin Zhong, Jing Qin, Mingyue Guo, Wangmeng Zuo + 1 more
Crowd counting is considered a challenging issue in computer vision. One of the most critical challenges in crowd counting is considering the impact of scale variations. Compared with other methods, better performance is achieved with CNN-based methods. However, given the limit of fixed geometric structures, the…
Zhen Dong, Dequan Wang, Qijing Huang, Yizhao Gao + 5 more
'Li Tian' 'Bichen Wu' 'Kurt Keutzer' 'John Wawrzynek'] Deploying deep learning models on embedded systems for computer vision tasks has been challenging due to limited compute resources and strict energy budgets. The majority of existing work focuses on accelerating image classification, while other fundamental vision…
Dawen Xu, Cheng Chu, Cheng Liu, Ying Wang + 3 more
'Kwang‐Ting Cheng'] Abstract—Deformable convolution networks (DCNs) proposed to address the image recognition with geometric or photometric variations typically involve deformable convolution that convolves on arbitrary locations of input features. The locations change with different inputs and induce considerable…
Peng Zhou, Hong Fang, Gaochang Wu, Hugo Aguas
Defects in photovoltaic (PV) panels can significantly reduce the power generation efficiency of the system and may cause localized overheating due to uneven current distribution. Therefore, adopting precise pixel-level defect detection, i.e., defect segmentation, technology is essential to ensuring stable operation.…
Daniel Tward, Timothy Brown, Yusuke Kageyama, Jaymin Patel + 5 more
This paper examines the problem of diffeomorphic image mapping in the presence of differing image intensity profiles and missing data. Our motivation comes from the problem of aligning 3D brain MRI with 100 micron isotropic resolution, to histology sections with 1 micron in plane resolution. Multiple stains, as well as…
Md. Aminur Rab Ratul, Mohammad Hamed Mozaffari, Enea Parimbelli, WonSook Lee
Skin cancer is a crucial public health issue and by far the most usual kind of cancer specifically in the region of North America. It is estimated that in 2019, only because of melanoma nearly 7,230 people will die, and 192,310 cases of malignant melanoma will be diagnosed. Nonetheless, nearly all types of skin lesions…
Md. Aminur Rab Ratul, M. Hamed Mozaffari, Won-Sook Lee, Enea Parimbelli
The prediction of skin lesions is a challenging task even for experienced dermatologists due to a little contrast between surrounding skin and lesions, the visual resemblance between skin lesions, fuddled lesion border, etc. An automated computer-aided detection system with given images can help clinicians to prognosis…
Wenyan Bi, Peiran Jin, Hendrikje Nienborg, Bei Xiao
Cloth is a common material and humans can visually estimate its mechanical properties by observing how it deforms under external forces. Here we ask whether, and how, dynamic deformation can affect the perception of mechanical properties of cloth. In Experiment 1, we find that both intrinsic mechanical properties and…
Authors not listed
Obtaining quantitative information about residence time behavior (i.e., the residence time distribution function) in realistic experimental systems is oftentimes experimentally challenging and numerically complex. The conventional way is to conduct very simple pulse or step tracer experiments or construct elaborate…
Ruiming Cao, Nikita Divekar, James Nuñez, Srigokul Upadhyayula + 1 more
Computational imaging reconstructions from multiple measurements that are captured sequentially often suffer from motion artifacts if the scene is dynamic. We propose a neural space-time model (NSTM) that jointly estimates the scene and its motion dynamics. Hence, we can both remove motion artifacts and resolve sample…
Kelsey Hatzell, Yanjie Zheng
X-ray Computed Tomography (CT) is a non-invasive, non-destructive approach to imaging materials, material systems and engineered components in two- and three- dimensions. Acquisition of 3D images requires the collection of hundreds or thousands of through-thickness X-ray radiographic images from different angles. Such…
Sanket Kadulkar, Michael Howard, Thomas Truskett, Venkat Ganesan
We develop a convolutional neural network (CNN) model to predict the diffusivity of cations in nanoparticle-based electrolytes, and use it to identify the characteristics of morphologies which exhibit optimal transport properties. The ground truth data is obtained from kinetic Monte Carlo (kMC) simulations of cation…