no code implementations • 15 Mar 2024 • Xiangtian Xue, Jiasong Wu, Youyong Kong, Lotfi Senhadji, Huazhong Shu
We transcend the limitation of traditional attention mechanisms that only focus on existing visual features by introducing deformable feature alignment to hierarchically refine spatial positioning fused with multi-scale visual and linguistic information.
no code implementations • 14 Mar 2024 • Xiangtian Xue, Jiasong Wu, Youyong Kong, Lotfi Senhadji, Huazhong Shu
Referring object removal refers to removing the specific object in an image referred by natural language expressions and filling the missing region with reasonable semantics.
1 code implementation • 13 Mar 2024 • Fuzhi Wu, Jiasong Wu, Youyong Kong, Chunfeng Yang, Guanyu Yang, Huazhong Shu, Guy Carrault, Lotfi Senhadji
Responding to these complexities, we introduce a novel framework, the Multiscale Low-Frequency Memory (MLFM) Network, with the goal to harness the full potential of CNNs while keeping their complexity unchanged.
no code implementations • 5 Feb 2024 • Qixiang Ma, Antoine Łucas, Huazhong Shu, Adrien Kaladji, Pascal Haigron
On the local dataset, our weakly-supervised learning approach based on pseudo labels outperforms strong-label-based fully-supervised learning (1. 54\% of Dice score on average), reducing labeling time by around 82. 0\%.
1 code implementation • 15 Jun 2022 • Jiacheng Shi, Yuting He, Youyong Kong, Jean-Louis Coatrieux, Huazhong Shu, Guanyu Yang, Shuo Li
An effective backbone network is important to deep learning-based Deformable Medical Image Registration (DMIR), because it extracts and matches the features between two images to discover the mutual correspondence for fine registration.
2 code implementations • 10 May 2022 • Zhangfu Dong, Yuting He, Xiaoming Qi, Yang Chen, Huazhong Shu, Jean-Louis Coatrieux, Guanyu Yang, Shuo Li
The nature of thick-slice scanning causes severe inter-slice discontinuities of 3D medical images, and the vanilla 2D/3D convolutional neural networks (CNNs) fail to represent sparse inter-slice information and dense intra-slice information in a balanced way, leading to severe underfitting to inter-slice features (for vanilla 2D CNNs) and overfitting to noise from long-range slices (for vanilla 3D CNNs).
1 code implementation • 30 Oct 2021 • Jiasong Wu, Qingchun Li, Guanyu Yang, Lei LI, Lotfi Senhadji, Huazhong Shu
The first module adopts a random audio sub-sampler on each noisy audio to generate training pairs.
no code implementations • 8 Jun 2021 • Yuting He, Rongjun Ge, Xiaoming Qi, Guanyu Yang, Yang Chen, Youyong Kong, Huazhong Shu, Jean-Louis Coatrieux, Shuo Li
3)We propose the adversarial weighted ensemble module which uses the trained discriminators to evaluate the quality of segmented structures, and normalizes these evaluation scores for the ensemble weights directed at the input image, thus enhancing the ensemble results.
no code implementations • ECCV 2020 • Yuting He, Tiantian Li, Guanyu Yang, Youyong Kong, Yang Chen, Huazhong Shu, Jean-Louis Coatrieux, Jean-Louis Dillenseger, Shuo Li
Deep learning-based medical image registration and segmentation joint models utilize the complementarity (augmentation data or weakly supervised data from registration, region constraints from segmentation) to bring mutual improvement in complex scene and few-shot situation.
no code implementations • 28 Jul 2020 • Jiasong Wu, Jing Zhang, Fuzhi Wu, Youyong Kong, Guanyu Yang, Lotfi Senhadji, Huazhong Shu
In order to solve or alleviate the synchronous training difficult problems of GANs and VAEs, recently, researchers propose Generative Scattering Networks (GSNs), which use wavelet scattering networks (ScatNets) as the encoder to obtain the features (or ScatNet embeddings) and convolutional neural networks (CNNs) as the decoder to generate the image.
1 code implementation • 21 Jul 2020 • Jiasong Wu, Xuan Li, Taotao Li, Fanman Meng, Youyong Kong, Guanyu Yang, Lotfi Senhadji, Huazhong Shu
We design a general deep learning network for learning the combination of three modalities, audio, face, and sign language information, for better solving the speech separation problem.
no code implementations • 8 Mar 2020 • Li Liu, Da Chen, Ming-Lei Shu, Baosheng Li, Huazhong Shu, Michel Paques, Laurent D. Cohen
Tubular structure tracking is a crucial task in the fields of computer vision and medical image analysis.
no code implementations • 20 Dec 2019 • Da Chen, Jean-Marie Mirebeau, Huazhong Shu, Laurent D. Cohen
In this paper, we introduce a new variational image segmentation model based on the minimal geodesic path framework and the eikonal PDE, where the region-based appearance term that defines then regional homogeneity features can be taken into account for estimating the associated minimal geodesic paths.
no code implementations • 20 Mar 2019 • Jiasong Wu, Ling Xu, Youyong Kong, Lotfi Senhadji, Huazhong Shu
In recent years, the deep complex networks (DCNs) and the deep quaternion networks (DQNs) have attracted more and more attentions.
no code implementations • 6 Mar 2019 • Jiasong Wu, Hongshan Ren, Youyong Kong, Chunfeng Yang, Lotfi Senhadji, Huazhong Shu
Although convolutional neural network (CNN) has made great progress, large redundant parameters restrict its deployment on embedded devices, especially mobile devices.
no code implementations • 27 Feb 2019 • Jinpeng Xia, Jiasong Wu, Youyong Kong, Pinzheng Zhang, Lotfi Senhadji, Huazhong Shu
Although Convolutional Neural Networks (CNNs) achieve effectiveness in various computer vision tasks, the significant requirement of storage of such networks hinders the deployment on computationally limited devices.
no code implementations • 27 Feb 2019 • Jiasong Wu, Fuzhi Wu, Qihan Yang, Youyong Kong, Xilin Liu, Yan Zhang, Lotfi Senhadji, Huazhong Shu
One of the key challenges in the area of signal processing on graphs is to design transforms and dictionaries methods to identify and exploit structure in signals on weighted graphs.
no code implementations • 14 Nov 2018 • Xu Han, Laurent Albera, Amar Kachenoura, Huazhong Shu, Lotfi Senhadji
Based on the low-rank property and an over-estimation of the core tensor, this joint estimation problem is solved by promoting (group) sparsity of the over-estimated core tensor.
no code implementations • 30 Jun 2018 • Li Liu, Jiasong Wu, Dengwang Li, Lotfi Senhadji, Huazhong Shu
Results: The error rates for different fractional orders of FrScatNet are examined and show that the classification accuracy is significantly improved in fractional scattering domain.
no code implementations • 22 Feb 2017 • Jiasong Wu, Shijie Qiu, Youyong Kong, Yang Chen, Lotfi Senhadji, Huazhong Shu
In this paper, we propose a new simple and learning-free deep learning network named MomentsNet, whose convolution layer, nonlinear processing layer and pooling layer are constructed by Moments kernels, binary hashing and block-wise histogram, respectively.
no code implementations • 12 May 2016 • Yu-An Wang, Guy Carrault, Alain Beuchee, Nathalie Costet, Huazhong Shu, Lotfi Senhadji
The objective of this paper was to determine if HRV, respiration and their relationships help to diagnose infection in premature infants via non-invasive ways in NICU.
no code implementations • 3 Mar 2016 • Jiasong Wu, Shijie Qiu, Youyong Kong, Longyu Jiang, Lotfi Senhadji, Huazhong Shu
The principal component analysis network (PCANet), which is one of the recently proposed deep learning architectures, achieves the state-of-the-art classification accuracy in various databases.
no code implementations • 20 Dec 2015 • Dan Wu, Jiasong Wu, Rui Zeng, Longyu Jiang, Lotfi Senhadji, Huazhong Shu
In order to classify the nonlinear feature with linear classifier and improve the classification accuracy, a deep learning network named kernel principal component analysis network (KPCANet) is proposed.
no code implementations • 5 Mar 2015 • Rui Zeng, Jiasong Wu, Zhuhong Shao, Yang Chen, Lotfi Senhadji, Huazhong Shu
The Principal Component Analysis Network (PCANet), which is one of the recently proposed deep learning architectures, achieves the state-of-the-art classification accuracy in various databases.
no code implementations • 5 Nov 2014 • Rui Zeng, Jiasong Wu, Lotfi Senhadji, Huazhong Shu
The MLDANet is a variation of linear discriminant analysis network (LDANet) and principal component analysis network (PCANet), both of which are the recently proposed deep learning algorithms.
no code implementations • 5 Nov 2014 • Rui Zeng, Jiasong Wu, Zhuhong Shao, Lotfi Senhadji, Huazhong Shu
The recently proposed principal component analysis network (PCANet) has been proved high performance for visual content classification.
no code implementations • 24 Jul 2014 • Jiasong Wu, Longyu Jiang, Xu Han, Lotfi Senhadji, Huazhong Shu
Texture plays an important role in many image analysis applications.
no code implementations • 12 Mar 2014 • Guanyu Yang, Huazhong Shu, Christine Toumoulin, Guo-Niu Han, Limin M. Luo
Because their computation by a direct method is very time expensive, recent efforts have been devoted to the reduction of computational complexity.
no code implementations • 12 Mar 2014 • Huazhong Shu, Jian Zhou, Guo-Niu Han, Limin M. Luo, Jean-Louis Coatrieux
A set of orthonormal polynomials is proposed for image reconstruction from projection data.