no code implementations • 5 Feb 2024 • Shanshan Wang, Ruoyou Wu, Sen Jia, Alou Diakite, Cheng Li, Qiegen Liu, Leslie Ying
The traits and trends of these techniques have also been given which have shifted from supervised learning to semi-supervised learning, and finally, to unsupervised learning methods.
no code implementations • 30 Aug 2023 • Zhuo-Xu Cui, Congcong Liu, Xiaohong Fan, Chentao Cao, Jing Cheng, Qingyong Zhu, Yuanyuan Liu, Sen Jia, Yihang Zhou, Haifeng Wang, Yanjie Zhu, Jianping Zhang, Qiegen Liu, Dong Liang
In order to enhance interpretability and overcome the acceleration limitations, this paper introduces an interpretable framework that unifies both $k$-space interpolation techniques and image-domain methods, grounded in the physical principles of heat diffusion equations.
no code implementations • 11 Apr 2023 • Zhuo-Xu Cui, Chentao Cao, Yue Wang, Sen Jia, Jing Cheng, Xin Liu, Hairong Zheng, Dong Liang, Yanjie Zhu
To overcome this challenge, we introduce a novel approach called SPIRiT-Diffusion, which is a diffusion model for k-space interpolation inspired by the iterative self-consistent SPIRiT method.
no code implementations • 14 Dec 2022 • Chentao Cao, Zhuo-Xu Cui, Jing Cheng, Sen Jia, Hairong Zheng, Dong Liang, Yanjie Zhu
Diffusion model is the most advanced method in image generation and has been successfully applied to MRI reconstruction.
1 code implementation • 11 Aug 2022 • Zhuo-Xu Cui, Sen Jia, Qingyong Zhu, Congcong Liu, Zhilang Qiu, Yuanyuan Liu, Jing Cheng, Haifeng Wang, Yanjie Zhu, Dong Liang
Recently, untrained neural networks (UNNs) have shown satisfactory performances for MR image reconstruction on random sampling trajectories without using additional full-sampled training data.
no code implementations • 8 Aug 2022 • Juan Zou, Cheng Li, Sen Jia, Ruoyou Wu, Tingrui Pei, Hairong Zheng, Shanshan Wang
Lately, deep learning has been extensively investigated for accelerating dynamic magnetic resonance (MR) imaging, with encouraging progresses achieved.
no code implementations • Remote Sensing of Environment 2022 • Meng Xu, Furong Deng, Sen Jia, Xiuping Jia, Antonio J. Plaza
First, attention maps of the input cloudy images are generated to extract the cloud distributions and features through an attentive recurrent network.
no code implementations • 9 Mar 2022 • Sen Jia, Yifan Wang
However, CNN-based methods are difficult to capture long-range dependencies, and also require a large amount of labeled data for model training. Besides, most of the self-supervised training methods in the field of HSI classification are based on the reconstruction of input samples, and it is difficult to achieve effective use of unlabeled samples.
no code implementations • 18 Dec 2021 • Zhuo-Xu Cui, Jing Cheng, Qingyong Zhu, Yuanyuan Liu, Sen Jia, Kankan Zhao, Ziwen Ke, Wenqi Huang, Haifeng Wang, Yanjie Zhu, Dong Liang
Specifically, focusing on accelerated MRI, we unroll a zeroth-order algorithm, of which the network module represents the regularizer itself, so that the network output can be still covered by the regularization model.
1 code implementation • 3 Dec 2021 • Sen Jia, Shuguo Jiang, Zhijie Lin, Nanying Li, Meng Xu, Shiqi Yu
In general, deep learning models often contain many trainable parameters and require a massive number of labeled samples to achieve optimal performance.
no code implementations • 20 Oct 2021 • Md Amirul Islam, Matthew Kowal, Sen Jia, Konstantinos G. Derpanis, Neil D. B. Bruce
Extensive experiments demonstrate the high quality of our generated pseudo-labels and effectiveness of the proposed framework in a variety of domains.
1 code implementation • ICCV 2021 • Md Amirul Islam, Matthew Kowal, Sen Jia, Konstantinos G. Derpanis, Neil D. B. Bruce
In this paper, we challenge the common assumption that collapsing the spatial dimensions of a 3D (spatial-channel) tensor in a convolutional neural network (CNN) into a vector via global pooling removes all spatial information.
1 code implementation • 12 Aug 2021 • Zhiyu Zhu, Hui Liu, Junhui Hou, Sen Jia, Qingfu Zhang
Then, we design a lightweight neural network with a multi-stage architecture to mimic the formed amended gradient descent process, in which efficient convolution and novel spectral zero-mean normalization are proposed to effectively extract spatial-spectral features for regressing an initialization, a basic gradient, and an incremental gradient.
no code implementations • 14 Jul 2021 • Meng Xu, Zhihao Wang, Jiasong Zhu, Xiuping Jia, Sen Jia
The main body of the generator contains two blocks; one is the pyramidal convolution in the residual-dense block (PCRDB), and the other is the attention-based upsample (AUP) block.
no code implementations • 13 Apr 2021 • Wenqi Huang, Sen Jia, Ziwen Ke, Zhuo-Xu Cui, Jing Cheng, Yanjie Zhu, Dong Liang
Improving the image resolution and acquisition speed of magnetic resonance imaging (MRI) is a challenging problem.
1 code implementation • 9 Mar 2021 • Ziwen Ke, Zhuo-Xu Cui, Wenqi Huang, Jing Cheng, Sen Jia, Haifeng Wang, Xin Liu, Hairong Zheng, Leslie Ying, Yanjie Zhu, Dong Liang
The nonlinear manifold is designed to characterize the temporal correlation of dynamic signals.
no code implementations • 28 Jan 2021 • Md Amirul Islam, Matthew Kowal, Sen Jia, Konstantinos G. Derpanis, Neil D. B. Bruce
; (ii) Does position encoding affect the learning of semantic representations?
no code implementations • 27 Jan 2021 • Md Amirul Islam, Matthew Kowal, Patrick Esser, Sen Jia, Bjorn Ommer, Konstantinos G. Derpanis, Neil Bruce
Contrasting the previous evidence that neurons in the later layers of a Convolutional Neural Network (CNN) respond to complex object shapes, recent studies have shown that CNNs actually exhibit a `texture bias': given an image with both texture and shape cues (e. g., a stylized image), a CNN is biased towards predicting the category corresponding to the texture.
no code implementations • ICLR 2021 • Md Amirul Islam, Matthew Kowal, Patrick Esser, Sen Jia, Björn Ommer, Konstantinos G. Derpanis, Neil Bruce
Contrasting the previous evidence that neurons in the later layers of a Convolutional Neural Network (CNN) respond to complex object shapes, recent studies have shown that CNNs actually exhibit a 'texture bias': given an image with both texture and shape cues (e. g., a stylized image), a CNN is biased towards predicting the category corresponding to the texture.
no code implementations • 1 Jan 2021 • Md Amirul Islam, Matthew Kowal, Sen Jia, Konstantinos G. Derpanis, Neil Bruce
Finally, we demonstrate the implications of these findings on a number of real-world tasks to show that position information can act as a feature or a bug.
no code implementations • 9 Nov 2020 • Qing Li, Jiasong Zhu, Jun Liu, Rui Cao, Qingquan Li, Sen Jia, Guoping Qiu
Despite the rapid progress in this topic, there are lacking of a comprehensive review, which is needed to summarize the current progress and provide the future directions.
1 code implementation • 26 Oct 2020 • Wenqi Huang, Ziwen Ke, Zhuo-Xu Cui, Jing Cheng, Zhilang Qiu, Sen Jia, Leslie Ying, Yanjie Zhu, Dong Liang
However, the selection of the parameters of L+S is empirical, and the acceleration rate is limited, which are common failings of iterative compressed sensing MR imaging (CS-MRI) reconstruction methods.
no code implementations • 22 Jun 2020 • Ziwen Ke, Wenqi Huang, Jing Cheng, Zhuoxu Cui, Sen Jia, Haifeng Wang, Xin Liu, Hairong Zheng, Leslie Ying, Yanjie Zhu, Dong Liang
The deep learning methods have achieved attractive performance in dynamic MR cine imaging.
1 code implementation • CVPR 2020 • Sen Jia, Neil D. B. Bruce
Our experiment shows FN-AUC can measure spatial biases, central and peripheral, more effectively than S-AUC without penalizing the fixation locations.
1 code implementation • ICLR 2020 • Md Amirul Islam, Sen Jia, Neil D. B. Bruce
In contrast to fully connected networks, Convolutional Neural Networks (CNNs) achieve efficiency by learning weights associated with local filters with a finite spatial extent.
1 code implementation • IEEE Transactions on Geoscience and Remote Sensing 2019 • Bin Deng, Sen Jia, Daming Shi
In the first task, when only a few labeled samples are available, we employ ideas from metric learning based on deep embedding features and make a similarity learning between pairs of samples.
Few-Shot Image Classification Hyperspectral Image Classification +3
no code implementations • 8 Jan 2019 • Sen Jia, Neil D. B. Bruce
Recent Salient Object Detection (SOD) systems are mostly based on Convolutional Neural Networks (CNNs).
no code implementations • 30 Sep 2018 • Shan-Shan Wang, Ziwen Ke, Huitao Cheng, Sen Jia, Ying Leslie, Hairong Zheng, Dong Liang
Dynamic MR image reconstruction from incomplete k-space data has generated great research interest due to its capability in reducing scan time.
no code implementations • 16 Jun 2018 • Sen Jia, Thomas Lansdall-Welfare, Nello Cristianini
We consider the problem of a neural network being requested to classify images (or other inputs) without making implicit use of a "protected concept", that is a concept that should not play any role in the decision of the network.
no code implementations • 2 May 2018 • Sen Jia, Neil D. B. Bruce
Furthermore, the encoder can contain more than one CNN model to extract features, and models can have different architectures or be pre-trained on different datasets.