Search Results for author: Hongming Shan

Found 71 papers, 37 papers with code

SPICE: Semantic Pseudo-labeling for Image Clustering

1 code implementation17 Mar 2021 Chuang Niu, Hongming Shan, Ge Wang

In this paper, we present a Semantic Pseudo-labeling-based Image ClustEring (SPICE) framework, which divides the clustering network into a feature model for measuring the instance-level similarity and a clustering head for identifying the cluster-level discrepancy.

Clustering Contrastive Learning +5

Temporal Modeling Matters: A Novel Temporal Emotional Modeling Approach for Speech Emotion Recognition

1 code implementation14 Nov 2022 Jiaxin Ye, Xin-Cheng Wen, Yujie Wei, Yong Xu, KunHong Liu, Hongming Shan

Specifically, TIM-Net first employs temporal-aware blocks to learn temporal affective representation, then integrates complementary information from the past and the future to enrich contextual representations, and finally, fuses multiple time scale features for better adaptation to the emotional variation.

Speech Emotion Recognition

Learning Representation for Clustering via Prototype Scattering and Positive Sampling

1 code implementation23 Nov 2021 Zhizhong Huang, Jie Chen, Junping Zhang, Hongming Shan

The strengths of ProPos are avoidable class collision issue, uniform representations, well-separated clusters, and within-cluster compactness.

Clustering Contrastive Learning +3

Twin Contrastive Learning with Noisy Labels

1 code implementation CVPR 2023 Zhizhong Huang, Junping Zhang, Hongming Shan

In this paper, we present TCL, a novel twin contrastive learning model to learn robust representations and handle noisy labels for classification.

Contrastive Learning Learning with noisy labels

DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising

1 code implementation24 Aug 2021 Zhizhong Huang, Junping Zhang, Yi Zhang, Hongming Shan

To better regularize the LDCT denoising model, this paper proposes a novel method, termed DU-GAN, which leverages U-Net based discriminators in the GANs framework to learn both global and local difference between the denoised and normal-dose images in both image and gradient domains.

Denoising

Point, Segment and Count: A Generalized Framework for Object Counting

1 code implementation21 Nov 2023 Zhizhong Huang, Mingliang Dai, Yi Zhang, Junping Zhang, Hongming Shan

In this paper, we propose a generalized framework for both few-shot and zero-shot object counting based on detection.

Knowledge Distillation Object +3

PFA-GAN: Progressive Face Aging with Generative Adversarial Network

2 code implementations7 Dec 2020 Zhizhong Huang, Shouzhen Chen, Junping Zhang, Hongming Shan

Although impressive results have been achieved with conditional generative adversarial networks (cGANs), the existing cGANs-based methods typically use a single network to learn various aging effects between any two different age groups.

Age Estimation Generative Adversarial Network

Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?

1 code implementation8 Nov 2018 Hongming Shan, Atul Padole, Fatemeh Homayounieh, Uwe Kruger, Ruhani Doda Khera, Chayanin Nitiwarangkul, Mannudeep K. Kalra, Ge Wang

Here we design a novel neural network architecture for low-dose CT (LDCT) and compare it with commercial iterative reconstruction methods used for standard of care CT.

Denoising Image Reconstruction

Adaptive Nonlinear Latent Transformation for Conditional Face Editing

1 code implementation ICCV 2023 Zhizhong Huang, Siteng Ma, Junping Zhang, Hongming Shan

This paper proposes a novel adaptive nonlinear latent transformation for disentangled and conditional face editing, termed AdaTrans.

Disentanglement

Prompt-In-Prompt Learning for Universal Image Restoration

1 code implementation8 Dec 2023 Zilong Li, Yiming Lei, Chenglong Ma, Junping Zhang, Hongming Shan

Second, we devise a novel prompt-to-prompt interaction module to fuse these two prompts into a universal restoration prompt.

Deblurring Image Denoising +2

Content-Noise Complementary Learning for Medical Image Denoising

2 code implementations IEEE Transactions on Medical Imaging 2022 Mufeng Geng, Xiangxi Meng, Jiangyuan Yu, Lei Zhu, Lujia Jin, Zhe Jiang, Bin Qiu, Hui Li, Hanjing Kong, Jianmin Yuan, Kun Yang, Hongming Shan, Hongbin Han, Zhi Yang, Qiushi Ren, Yanye Lu

In this study, we propose a simple yet effective strategy, the content-noise complementary learning (CNCL) strategy, in which two deep learning predictors are used to learn the respective content and noise of the image dataset complementarily.

Generative Adversarial Network Image Denoising +1

Online Prototype Learning for Online Continual Learning

1 code implementation ICCV 2023 Yujie Wei, Jiaxin Ye, Zhizhong Huang, Junping Zhang, Hongming Shan

Online continual learning (CL) studies the problem of learning continuously from a single-pass data stream while adapting to new data and mitigating catastrophic forgetting.

Continual Learning Knowledge Distillation

Look globally, age locally: Face aging with an attention mechanism

1 code implementation24 Oct 2019 Haiping Zhu, Zhizhong Huang, Hongming Shan, Junping Zhang

Face aging is of great importance for cross-age recognition and entertainment-related applications.

MORPH

AgeFlow: Conditional Age Progression and Regression with Normalizing Flows

1 code implementation15 May 2021 Zhizhong Huang, Shouzhen Chen, Junping Zhang, Hongming Shan

Age progression and regression aim to synthesize photorealistic appearance of a given face image with aging and rejuvenation effects, respectively.

Attribute Knowledge Distillation +1

Quadratic Autoencoder (Q-AE) for Low-dose CT Denoising

1 code implementation17 Jan 2019 Fenglei Fan, Hongming Shan, Mannudeep K. Kalra, Ramandeep Singh, Guhan Qian, Matthew Getzin, Yueyang Teng, Juergen Hahn, Ge Wang

Inspired by complexity and diversity of biological neurons, our group proposed quadratic neurons by replacing the inner product in current artificial neurons with a quadratic operation on input data, thereby enhancing the capability of an individual neuron.

Image Denoising

CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalization

1 code implementation4 Apr 2023 Qi Gao, Zilong Li, Junping Zhang, Yi Zhang, Hongming Shan

First, CoreDiff utilizes LDCT images to displace the random Gaussian noise and employs a novel mean-preserving degradation operator to mimic the physical process of CT degradation, significantly reducing sampling steps thanks to the informative LDCT images as the starting point of the sampling process.

Computed Tomography (CT) Denoising +1

Cross-head Supervision for Crowd Counting with Noisy Annotations

1 code implementation16 Mar 2023 Mingliang Dai, Zhizhong Huang, Jiaqi Gao, Hongming Shan, Junping Zhang

To alleviate the negative impact of noisy annotations, we propose a novel crowd counting model with one convolution head and one transformer head, in which these two heads can supervise each other in noisy areas, called Cross-Head Supervision.

Crowd Counting

Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting

2 code implementations13 Jan 2022 Jiaqi Gao, Zhizhong Huang, Yiming Lei, Hongming Shan, James Z. Wang, Fei-Yue Wang, Junping Zhang

Specifically, we propose a Deep Rank-consistEnt pyrAmid Model (DREAM), which makes full use of rank consistency across coarse-to-fine pyramid features in latent spaces for enhanced crowd counting with massive unlabeled images.

Crowd Counting

ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising

1 code implementation23 Jul 2023 Zhihao Chen, Qi Gao, Yi Zhang, Hongming Shan

In this paper, we propose a novel Anatomy-aware Supervised CONtrastive learning framework, termed ASCON, which can explore the anatomical semantics for low-dose CT denoising while providing anatomical interpretability.

Anatomy Computed Tomography (CT) +2

Semantic Latent Decomposition with Normalizing Flows for Face Editing

1 code implementation11 Sep 2023 Binglei Li, Zhizhong Huang, Hongming Shan, Junping Zhang

Specifically, SDFlow decomposes the original latent code into different irrelevant variables by jointly optimizing two components: (i) a semantic encoder to estimate semantic variables from input faces and (ii) a flow-based transformation module to map the latent code into a semantic-irrelevant variable in Gaussian distribution, conditioned on the learned semantic variables.

FreeSeed: Frequency-band-aware and Self-guided Network for Sparse-view CT Reconstruction

1 code implementation12 Jul 2023 Chenglong Ma, Zilong Li, Junping Zhang, Yi Zhang, Hongming Shan

Specifically, we first propose a frequency-band-aware artifact modeling network (FreeNet), which learns artifact-related frequency-band attention in Fourier domain for better modeling the globally distributed streak artifact on the sparse-view CT images.

Computed Tomography (CT)

SelfGait: A Spatiotemporal Representation Learning Method for Self-supervised Gait Recognition

1 code implementation27 Mar 2021 Yiqun Liu, Yi Zeng, Jian Pu, Hongming Shan, Peiyang He, Junping Zhang

In this work, we propose a self-supervised gait recognition method, termed SelfGait, which takes advantage of the massive, diverse, unlabeled gait data as a pre-training process to improve the representation abilities of spatiotemporal backbones.

Gait Recognition Representation Learning

Emo-DNA: Emotion Decoupling and Alignment Learning for Cross-Corpus Speech Emotion Recognition

1 code implementation4 Aug 2023 Jiaxin Ye, Yujie Wei, Xin-Cheng Wen, Chenglong Ma, Zhizhong Huang, KunHong Liu, Hongming Shan

On one hand, our contrastive emotion decoupling achieves decoupling learning via a contrastive decoupling loss to strengthen the separability of emotion-relevant features from corpus-specific ones.

Cross-corpus Speech Emotion Recognition +1

Impact of loss functions on the performance of a deep neural network designed to restore low-dose digital mammography

1 code implementation12 Nov 2021 Hongming Shan, Rodrigo de Barros Vimieiro, Lucas Rodrigues Borges, Marcelo Andrade da Costa Vieira, Ge Wang

Results showed that the perceptual loss function (PL4) is able to achieve virtually the same noise levels of a full-dose acquisition, while resulting in smaller signal bias compared to other loss functions.

SAN-Net: Learning Generalization to Unseen Sites for Stroke Lesion Segmentation with Self-Adaptive Normalization

1 code implementation9 May 2022 Weiyi Yu, Zhizhong Huang, Junping Zhang, Hongming Shan

To tackle this issue, we introduce a self-adaptive normalization network, termed SAN-Net, to achieve adaptive generalization on unseen sites for stroke lesion segmentation.

Data Augmentation Lesion Segmentation

Parameter-Transferred Wasserstein Generative Adversarial Network (PT-WGAN) for Low-Dose PET Image Denoising

1 code implementation13 Oct 2019 Yu Gong, Hongming Shan, Yueyang Teng, Ning Tu, Ming Li, Guodong Liang, Ge Wang, Shan-Shan Wang

The contributions of this paper are twofold: i) a PT-WGAN framework is designed to denoise low-dose PET images without compromising structural details, and ii) a task-specific initialization based on transfer learning is developed to train PT-WGAN using trainable parameters transferred from a pretrained model, which significantly improves the training efficiency of PT-WGAN.

Generative Adversarial Network Image Denoising +1

Deep Efficient End-to-end Reconstruction (DEER) Network for Few-view Breast CT Image Reconstruction

1 code implementation9 Dec 2019 Huidong Xie, Hongming Shan, Wenxiang Cong, Chi Liu, Xiaohua Zhang, Shaohua Liu, Ruola Ning, Ge Wang

Breast CT provides image volumes with isotropic resolution in high contrast, enabling detection of small calcification (down to a few hundred microns in size) and subtle density differences.

Image Reconstruction

DreamVideo: Composing Your Dream Videos with Customized Subject and Motion

1 code implementation7 Dec 2023 Yujie Wei, Shiwei Zhang, Zhiwu Qing, Hangjie Yuan, Zhiheng Liu, Yu Liu, Yingya Zhang, Jingren Zhou, Hongming Shan

In motion learning, we architect a motion adapter and fine-tune it on the given videos to effectively model the target motion pattern.

Image Generation Video Generation

Prompted Contextual Transformer for Incomplete-View CT Reconstruction

1 code implementation13 Dec 2023 Chenglong Ma, Zilong Li, Junjun He, Junping Zhang, Yi Zhang, Hongming Shan

To enjoy the multi-setting synergy in a single model, we propose a novel Prompted Contextual Transformer (ProCT) for incomplete-view CT reconstruction.

Computed Tomography (CT)

LIT-Former: Linking In-plane and Through-plane Transformers for Simultaneous CT Image Denoising and Deblurring

1 code implementation21 Feb 2023 Zhihao Chen, Chuang Niu, Qi Gao, Ge Wang, Hongming Shan

Here, we propose to link in-plane and through-plane transformers for simultaneous in-plane denoising and through-plane deblurring, termed as LIT-Former, which can efficiently synergize in-plane and through-plane sub-tasks for 3D CT imaging and enjoy the advantages of both convolution and transformer networks.

Computed Tomography (CT) Deblurring +2

HOPE: Hybrid-granularity Ordinal Prototype Learning for Progression Prediction of Mild Cognitive Impairment

1 code implementation19 Jan 2024 Chenhui Wang, Yiming Lei, Tao Chen, Junping Zhang, Yuxin Li, Hongming Shan

Inspired by that various longitudinal biomarkers and cognitive measurements present an ordinal pathway on AD progression, we propose a novel Hybrid-granularity Ordinal PrototypE learning (HOPE) method to characterize AD ordinal progression for MCI progression prediction.

Low-dose CT Denoising with Language-engaged Dual-space Alignment

1 code implementation10 Mar 2024 Zhihao Chen, Tao Chen, Chenhui Wang, Chuang Niu, Ge Wang, Hongming Shan

While various deep learning methods were proposed for low-dose computed tomography (CT) denoising, they often suffer from over-smoothing, blurring, and lack of explainability.

Computed Tomography (CT) Denoising

Quad-Net: Quad-domain Network for CT Metal Artifact Reduction

1 code implementation24 Jul 2022 Zilong Li, Qi Gao, Yaping Wu, Chuang Niu, Junping Zhang, Meiyun Wang, Ge Wang, Hongming Shan

Here we extend the state-of-the-art dual-domain deep network approach into a quad-domain counterpart so that all the features in the sinogram, image, and their corresponding Fourier domains are synergized to eliminate metal artifacts optimally without compromising structural subtleties.

Computed Tomography (CT) Metal Artifact Reduction

Structure-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising

no code implementations2 May 2018 Chenyu You, Qingsong Yang, Hongming Shan, Lars Gjesteby, Guang Li, Shenghong Ju, Zhuiyang Zhang, Zhen Zhao, Yi Zhang, Wenxiang Cong, Ge Wang

However, the radiation dose reduction compromises the signal-to-noise ratio (SNR), leading to strong noise and artifacts that down-grade CT image quality.

Computed Tomography (CT) Denoising

3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network

no code implementations15 Feb 2018 Hongming Shan, Yi Zhang, Qingsong Yang, Uwe Kruger, Mannudeep K. Kalra, Ling Sun, Wenxiang Cong, Ge Wang

Based on the transfer learning from 2D to 3D, the 3D network converges faster and achieves a better denoising performance than that trained from scratch.

Computed Tomography (CT) Denoising +2

CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)

no code implementations10 Aug 2018 Chenyu You, Guang Li, Yi Zhang, Xiaoliu Zhang, Hongming Shan, Shenghong Ju, Zhen Zhao, Zhuiyang Zhang, Wenxiang Cong, Michael W. Vannier, Punam K. Saha, Ge Wang

Specifically, with the generative adversarial network (GAN) as the building block, we enforce the cycle-consistency in terms of the Wasserstein distance to establish a nonlinear end-to-end mapping from noisy LR input images to denoised and deblurred HR outputs.

Computed Tomography (CT) Generative Adversarial Network +2

Shape and Margin-Aware Lung Nodule Classification in Low-dose CT Images via Soft Activation Mapping

no code implementations30 Oct 2018 Yiming Lei, Yukun Tian, Hongming Shan, Junping Zhang, Ge Wang, Mannudeep Kalra

Therefore, CAM and Grad-CAM cannot provide optimal interpretation for lung nodule categorization task in low-dose CT images, in that fine-grained pathological clues like discrete and irregular shape and margins of nodules are capable of enhancing sensitivity and specificity of nodule classification with regards to CNN.

Data Augmentation General Classification +3

Super-resolution MRI through Deep Learning

no code implementations16 Oct 2018 Qing Lyu, Chenyu You, Hongming Shan, Ge Wang

Magnetic resonance imaging (MRI) is extensively used for diagnosis and image-guided therapeutics.

Medical Physics

Ordinal Distribution Regression for Gait-based Age Estimation

no code implementations27 May 2019 Haiping Zhu, Yuheng Zhang, Guohao Li, Junping Zhang, Hongming Shan

This paper proposes an ordinal distribution regression with a global and local convolutional neural network for gait-based age estimation.

Age Estimation regression

MRI Super-Resolution with Ensemble Learning and Complementary Priors

no code implementations6 Jul 2019 Qing Lyu, Hongming Shan, Ge Wang

Finally, a convolutional neural network is used for ensemble learning that synergizes the outputs of GANs into the final MR super-resolution images.

Ensemble Learning Generative Adversarial Network +1

Precipitation Nowcasting with Star-Bridge Networks

no code implementations18 Jul 2019 Yuan Cao, Qiuying Li, Hongming Shan, Zhizhong Huang, Lei Chen, Leiming Ma, Junping Zhang

Precipitation nowcasting, which aims to precisely predict the short-term rainfall intensity of a local region, is gaining increasing attention in the artificial intelligence community.

Video Prediction

Simultaneous reconstruction of the initial pressure and sound speed in photoacoustic tomography using a deep-learning approach

no code implementations23 Jul 2019 Hongming Shan, Christopher Wiedeman, Ge Wang, Yang Yang

Photoacoustic tomography seeks to reconstruct an acoustic initial pressure distribution from the measurement of the ultrasound waveforms.

Multi-Contrast Super-Resolution MRI Through a Progressive Network

no code implementations5 Aug 2019 Qing Lyu, Hongming Shan, Ge Wang

Our experimental results demonstrate that the proposed networks can produce MRI super-resolution images with good image quality and outperform other multi-contrast super-resolution methods in terms of structural similarity and peak signal-to-noise ratio.

Computed Tomography (CT) Image Super-Resolution

Deep-learning-based Breast CT for Radiation Dose Reduction

no code implementations25 Sep 2019 Wenxiang Cong, Hongming Shan, Xiaohua Zhang, Shaohua Liu, Ruola Ning, Ge Wang

In this study, we propose a deep-learning-based method to establish a residual neural network model for the image reconstruction, which is applied for few-view breast CT to produce high quality breast CT images.

Computed Tomography (CT) Image Reconstruction

Deep Encoder-decoder Adversarial Reconstruction (DEAR) Network for 3D CT from Few-view Data

no code implementations13 Nov 2019 Huidong Xie, Hongming Shan, Ge Wang

Few-view CT image reconstruction is one of the main ways to minimize radiation dose and potentially allow a stationary CT architecture.

Computed Tomography (CT) Image Reconstruction

Cine Cardiac MRI Motion Artifact Reduction Using a Recurrent Neural Network

no code implementations23 Jun 2020 Qing Lyu, Hongming Shan, Yibin Xie, Debiao Li, Ge Wang

As compared to computed tomography (CT), MRI, however, requires a long scan time, which inevitably induces motion artifacts and causes patients' discomfort.

Computed Tomography (CT) Metal Artifact Reduction +2

Low-dimensional Manifold Constrained Disentanglement Network for Metal Artifact Reduction

no code implementations8 Jul 2020 Chuang Niu, Wenxiang Cong, Fenglei Fan, Hongming Shan, Mengzhou Li, Jimin Liang, Ge Wang

Deep neural network based methods have achieved promising results for CT metal artifact reduction (MAR), most of which use many synthesized paired images for training.

Disentanglement Metal Artifact Reduction

Stabilizing Deep Tomographic Reconstruction

no code implementations4 Aug 2020 Weiwen Wu, Dianlin Hu, Wenxiang Cong, Hongming Shan, Shao-Yu Wang, Chuang Niu, Pingkun Yan, Hengyong Yu, Varut Vardhanabhuti, Ge Wang

ACID synergizes a deep reconstruction network trained on big data, kernel awareness from CS-inspired processing, and iterative refinement to minimize the data residual relative to real measurement.

Adversarial Attack Computed Tomography (CT) +1

Convolutional Ordinal Regression Forest for Image Ordinal Estimation

no code implementations7 Aug 2020 Haiping Zhu, Hongming Shan, Yuheng Zhang, Lingfu Che, Xiaoyang Xu, Junping Zhang, Jianbo Shi, Fei-Yue Wang

We propose a novel ordinal regression approach, termed Convolutional Ordinal Regression Forest or CORF, for image ordinal estimation, which can integrate ordinal regression and differentiable decision trees with a convolutional neural network for obtaining precise and stable global ordinal relationships.

Age Estimation Binary Classification +1

Meta Ordinal Regression Forest For Learning with Unsure Lung Nodules

no code implementations7 Dec 2020 Yiming Lei, Haiping Zhu, Junping Zhang, Hongming Shan

Recently, an unsure data model (UDM) was proposed to incorporate those unsure nodules by formulating this problem as an ordinal regression, showing better performance over traditional binary classification.

Binary Classification Classification +5

Meta ordinal weighting net for improving lung nodule classification

no code implementations31 Jan 2021 Yiming Lei, Hongming Shan, Junping Zhang

In this paper, we propose a Meta Ordinal Weighting Network (MOW-Net) to explicitly align each training sample with a meta ordinal set (MOS) containing a few samples from all classes.

Classification General Classification +3

RoutingGAN: Routing Age Progression and Regression with Disentangled Learning

no code implementations1 Feb 2021 Zhizhong Huang, Junping Zhang, Hongming Shan

Although impressive results have been achieved for age progression and regression, there remain two major issues in generative adversarial networks (GANs)-based methods: 1) conditional GANs (cGANs)-based methods can learn various effects between any two age groups in a single model, but are insufficient to characterize some specific patterns due to completely shared convolutions filters; and 2) GANs-based methods can, by utilizing several models to learn effects independently, learn some specific patterns, however, they are cumbersome and require age label in advance.

regression

MANAS: Multi-Scale and Multi-Level Neural Architecture Search for Low-Dose CT Denoising

no code implementations24 Mar 2021 Zexin Lu, Wenjun Xia, Yongqiang Huang, Hongming Shan, Hu Chen, Jiliu Zhou, Yi Zhang

Recent advance on neural network architecture search (NAS) has proved that the network architecture has a dramatic effect on the model performance, which indicates that current network architectures for LDCT may be sub-optimal.

Computed Tomography (CT) Denoising +1

Meta Ordinal Regression Forest for Medical Image Classification with Ordinal Labels

no code implementations15 Mar 2022 Yiming Lei, Haiping Zhu, Junping Zhang, Hongming Shan

To improve model generalization with ordinal information, we propose a novel meta ordinal regression forest (MORF) method for medical image classification with ordinal labels, which learns the ordinal relationship through the combination of convolutional neural network and differential forest in a meta-learning framework.

feature selection Image Classification +3

Convolutional Neural Network to Restore Low-Dose Digital Breast Tomosynthesis Projections in a Variance Stabilization Domain

no code implementations22 Mar 2022 Rodrigo de Barros Vimieiro, Chuang Niu, Hongming Shan, Lucas Rodrigues Borges, Ge Wang, Marcelo Andrade da Costa Vieira

To accurately control the network operation point, in terms of noise and blur of the restored image, we propose a loss function that minimizes the bias and matches residual noise between the input and the output.

Medical Diagnosis

Physics-/Model-Based and Data-Driven Methods for Low-Dose Computed Tomography: A survey

no code implementations29 Mar 2022 Wenjun Xia, Hongming Shan, Ge Wang, Yi Zhang

Since 2016, deep learning (DL) has advanced tomographic imaging with remarkable successes, especially in low-dose computed tomography (LDCT) imaging.

Denoising

When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework and A New Benchmark

no code implementations17 Oct 2022 Zhizhong Huang, Junping Zhang, Hongming Shan

Extensive experimental results on five benchmark cross-age datasets demonstrate that MTLFace yields superior performance for both AIFR and FAS.

Age-Invariant Face Recognition Face Generation +1

Motion Matters: A Novel Motion Modeling For Cross-View Gait Feature Learning

no code implementations21 Oct 2022 Jingqi Li, Jiaqi Gao, Yuzhen Zhang, Hongming Shan, Junping Zhang

Specifically, we first extract the motion features from the encoded motion sequences in the shallow layer.

Gait Recognition

CORE: Learning Consistent Ordinal REpresentations for Image Ordinal Estimation

no code implementations15 Jan 2023 Yiming Lei, Zilong Li, Yangyang Li, Junping Zhang, Hongming Shan

However, the manifold of the resultant feature representations does not maintain the intrinsic ordinal relations of interest, which hinders the effectiveness of the image ordinal estimation.

regression

BerDiff: Conditional Bernoulli Diffusion Model for Medical Image Segmentation

no code implementations10 Apr 2023 Tao Chen, Chenhui Wang, Hongming Shan

Second, by leveraging the stochastic nature of the diffusion model, our BerDiff randomly samples the initial Bernoulli noise and intermediate latent variables multiple times to produce a range of diverse segmentation masks, which can highlight salient regions of interest that can serve as valuable references for radiologists.

Image Segmentation Medical Image Segmentation +2

CLIP-Lung: Textual Knowledge-Guided Lung Nodule Malignancy Prediction

no code implementations17 Apr 2023 Yiming Lei, Zilong Li, Yan Shen, Junping Zhang, Hongming Shan

Drawing on the capability of the contrastive language-image pre-training (CLIP) model to learn generalized visual representations from text annotations, in this paper, we propose CLIP-Lung, a textual knowledge-guided framework for lung nodule malignancy prediction.

Attribute Contrastive Learning

FAN-Net: Fourier-Based Adaptive Normalization For Cross-Domain Stroke Lesion Segmentation

no code implementations23 Apr 2023 Weiyi Yu, Yiming Lei, Hongming Shan

To address this problem, we intend to change style information without affecting high-level semantics via adaptively changing the low-frequency amplitude components of the Fourier transform so as to enhance model robustness to varying domains.

Lesion Segmentation

ViP-Mixer: A Convolutional Mixer for Video Prediction

no code implementations20 Nov 2023 Xin Zheng, Ziang Peng, Yuan Cao, Hongming Shan, Junping Zhang

Video prediction aims to predict future frames from a video's previous content.

Video Prediction

Energizing Federated Learning via Filter-Aware Attention

no code implementations18 Nov 2023 Ziyuan Yang, Zerui Shao, Huijie Huangfu, Hui Yu, Andrew Beng Jin Teoh, Xiaoxiao Li, Hongming Shan, Yi Zhang

Federated learning (FL) is a promising distributed paradigm, eliminating the need for data sharing but facing challenges from data heterogeneity.

Federated Learning

IQAGPT: Image Quality Assessment with Vision-language and ChatGPT Models

no code implementations25 Dec 2023 Zhihao Chen, Bin Hu, Chuang Niu, Tao Chen, Yuxin Li, Hongming Shan, Ge Wang

Second, we fine-tune the image quality captioning VLM on the CT-IQA dataset to generate quality descriptions.

Image Quality Assessment

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