427 citations · 3.3k across the 77 of their papers we have counts for
79 papers
Noise2Match: Self-Supervised Low-Dose CT Denoising via Adaptive Inter-Slice Matching
Langrui Zhou, Guang Li, Xinyu Huang +5
With the rapid development of deep learning, supervised convolutional neural network methods have greatly improved the performance of low-dose computed tomography (CT) denoising. H…
Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models
Yifan Yuan, Xiangyu Liu, Hongming Shan +5
Although text-to-image diffusion models generally exhibit strong prompt-following ability, we identify a persistent and previously underexplored failure pattern in which a small su…
PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering
Xuqian Xue, Yiming Lei, Qi Cai +2
While contrastive multi-view clustering has achieved remarkable success, it implicitly assumes balanced class distribution. However, real-world multi-view data primarily exhibits c…
Radiologist-in-the-Loop Self-Training for Generalizable CT Metal Artifact Reduction
Chenglong Ma, Zilong Li, Yuanlin Li +5
Metal artifacts in computed tomography (CT) images can significantly degrade image quality and impede accurate diagnosis. Supervised metal artifact reduction (MAR) methods, trained…
Information-Maximized Soft Variable Discretization for Self-Supervised Image Representation Learning
Chuang Niu, Wenjun Xia, Hongming Shan +1
Self-supervised learning (SSL) has emerged as a crucial technique in image processing, encoding, and understanding, especially for developing today's vision foundation models that…
DepMamba: Progressive Fusion Mamba for Multimodal Depression Detection
Jiaxin Ye, Junping Zhang, Hongming Shan
Depression is a common mental disorder that affects millions of people worldwide. Although promising, current multimodal methods hinge on aligned or aggregated multimodal fusion, s…
Low-dose CT Denoising with Language-engaged Dual-space Alignment
Zhihao Chen, Tao Chen, Chenhui Wang +3
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. To a…
HOPE: Hybrid-granularity Ordinal Prototype Learning for Progression Prediction of Mild Cognitive Impairment
Chenhui Wang, Yiming Lei, Tao Chen +3
Mild cognitive impairment (MCI) is often at high risk of progression to Alzheimer's disease (AD). Existing works to identify the progressive MCI (pMCI) typically require MCI subtyp…
Prompt-In-Prompt Learning for Universal Image Restoration
Zilong Li, Yiming Lei, Chenglong Ma +2
Image restoration, which aims to retrieve and enhance degraded images, is fundamental across a wide range of applications. While conventional deep learning approaches have notably…
Prompted Contextual Transformer for Incomplete-View CT Reconstruction
Chenglong Ma, Zilong Li, Junjun He +3
Incomplete-view computed tomography (CT) can shorten the data acquisition time and allow scanning of large objects, including sparse-view and limited-angle scenarios, each with var…
Energizing Federated Learning via Filter-Aware Attention
Ziyuan Yang, Zerui Shao, Huijie Huangfu +5
Federated learning (FL) is a promising distributed paradigm, eliminating the need for data sharing but facing challenges from data heterogeneity. Personalized parameter generation…
Point, Segment and Count: A Generalized Framework for Object Counting
Zhizhong Huang, Mingliang Dai, Yi Zhang +2
Class-agnostic object counting aims to count all objects in an image with respect to example boxes or class names, \emph{a.k.a} few-shot and zero-shot counting. In this paper, we p…
SIAM: A Simple Alternating Mixer for Video Prediction
Xin Zheng, Ziang Peng, Yuan Cao +2
Video prediction, predicting future frames from the previous ones, has broad applications such as autonomous driving and weather forecasting. Existing state-of-the-art methods typi…
LICO: Explainable Models with Language-Image Consistency
Yiming Lei, Zilong Li, Yangyang Li +2
Interpreting the decisions of deep learning models has been actively studied since the explosion of deep neural networks. One of the most convincing interpretation approaches is sa…
Semantic Latent Decomposition with Normalizing Flows for Face Editing
Binglei Li, Zhizhong Huang, Hongming Shan +1
Navigating in the latent space of StyleGAN has shown effectiveness for face editing. However, the resulting methods usually encounter challenges in complicated navigation due to th…
Learning to Distill Global Representation for Sparse-View CT
Zilong Li, Chenglong Ma, Jie Chen +2
Sparse-view computed tomography (CT) -- using a small number of projections for tomographic reconstruction -- enables much lower radiation dose to patients and accelerated data acq…
Emo-DNA: Emotion Decoupling and Alignment Learning for Cross-Corpus Speech Emotion Recognition
Jiaxin Ye, Yujie Wei, Xin-Cheng Wen +4
Cross-corpus speech emotion recognition (SER) seeks to generalize the ability of inferring speech emotion from a well-labeled corpus to an unlabeled one, which is a rather challeng…
Online Prototype Learning for Online Continual Learning
Yujie Wei, Jiaxin Ye, Zhizhong Huang +2
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. Recent…
ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising
Zhihao Chen, Qi Gao, Yi Zhang +1
While various deep learning methods have been proposed for low-dose computed tomography (CT) denoising, most of them leverage the normal-dose CT images as the ground-truth to super…
Adaptive Nonlinear Latent Transformation for Conditional Face Editing
Zhizhong Huang, Siteng Ma, Junping Zhang +1
Recent works for face editing usually manipulate the latent space of StyleGAN via the linear semantic directions. However, they usually suffer from the entanglement of facial attri…
FreeSeed: Frequency-band-aware and Self-guided Network for Sparse-view CT Reconstruction
Chenglong Ma, Zilong Li, Junping Zhang +2
Sparse-view computed tomography (CT) is a promising solution for expediting the scanning process and mitigating radiation exposure to patients, the reconstructed images, however, c…
FAN-Net: Fourier-Based Adaptive Normalization For Cross-Domain Stroke Lesion Segmentation
Weiyi Yu, Yiming Lei, Hongming Shan
Since stroke is the main cause of various cerebrovascular diseases, deep learning-based stroke lesion segmentation on magnetic resonance (MR) images has attracted considerable atte…
CLIP-Lung: Textual Knowledge-Guided Lung Nodule Malignancy Prediction
Yiming Lei, Zilong Li, Yan Shen +2
Lung nodule malignancy prediction has been enhanced by advanced deep-learning techniques and effective tricks. Nevertheless, current methods are mainly trained with cross-entropy l…
BerDiff: Conditional Bernoulli Diffusion Model for Medical Image Segmentation
Tao Chen, Chenhui Wang, Hongming Shan
Medical image segmentation is a challenging task with inherent ambiguity and high uncertainty, attributed to factors such as unclear tumor boundaries and multiple plausible annotat…