Search Results for author: Huazhong Shu

Found 29 papers, 5 papers with code

ST-LDM: A Universal Framework for Text-Grounded Object Generation in Real Images

no code implementations15 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.

Denoising

Rethinking Referring Object Removal

no code implementations14 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.

Object

Multiscale Low-Frequency Memory Network for Improved Feature Extraction in Convolutional Neural Networks

1 code implementation13 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.

Image Classification Image-to-Image Translation +1

Beyond Strong labels: Weakly-supervised Learning Based on Gaussian Pseudo Labels for The Segmentation of Ellipse-like Vascular Structures in Non-contrast CTs

no code implementations5 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\%.

Weakly-supervised Learning

XMorpher: Full Transformer for Deformable Medical Image Registration via Cross Attention

1 code implementation15 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.

Deformable Medical Image Registration Image Registration +2

MNet: Rethinking 2D/3D Networks for Anisotropic Medical Image Segmentation

2 code implementations10 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).

Image Segmentation Medical Image Segmentation +1

Self-Supervised Speech Denoising Using Only Noisy Audio Signals

1 code implementation30 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.

Audio Denoising Denoising +1

EnMcGAN: Adversarial Ensemble Learning for 3D Complete Renal Structures Segmentation

no code implementations8 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.

Ensemble Learning Segmentation

Deep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical Images

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.

Image Registration Medical Image Registration +1

Generative networks as inverse problems with fractional wavelet scattering networks

no code implementations28 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.

Image Generation

CSLNSpeech: solving extended speech separation problem with the help of Chinese sign language

1 code implementation21 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.

Self-Supervised Learning Speech Separation

Trajectory Grouping with Curvature Regularization for Tubular Structure Tracking

no code implementations8 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.

A Region-based Randers Geodesic Approach for Image Segmentation

no code implementations20 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.

Boundary Detection Image Segmentation +2

Deep Octonion Networks

no code implementations20 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.

General Classification Image Classification +1

Compressing complex convolutional neural network based on an improved deep compression algorithm

no code implementations6 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.

Fractional spectral graph wavelets and their applications

no code implementations27 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.

Modulated binary cliquenet

no code implementations27 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.

Robust low-rank multilinear tensor approximation for a joint estimation of the multilinear rank and the loading matrices

no code implementations14 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.

Tensor Decomposition

Fractional Wavelet Scattering Network and Applications

no code implementations30 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.

General Classification Image Classification +1

MomentsNet: a simple learning-free method for binary image recognition

no code implementations22 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.

Heart Rate Variability and Respiration Signal as Diagnostic Tools for Late Onset Sepsis in Neonatal Intensive Care Units

no code implementations12 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.

Heart Rate Variability

PCANet: An energy perspective

no code implementations3 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.

General Classification

Kernel principal component analysis network for image classification

no code implementations20 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.

Classification Face Recognition +3

Color Image Classification via Quaternion Principal Component Analysis Network

no code implementations5 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.

Classification General Classification +1

Multilinear Principal Component Analysis Network for Tensor Object Classification

no code implementations5 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.

Classification General Classification +1

Tensor object classification via multilinear discriminant analysis network

no code implementations5 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.

Classification General Classification +1

Efficient Legendre moment computation for grey level images

no code implementations12 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.