Purify-then-Align: Towards Robust Human Sensing under Modality Missing with Knowledge Distillation from Noisy Multimodal Teacher
School of Software Engineering, Xi’an Jiaotong University（西安交通大学软件工程学院）；Institute of Computer Science, Universität Bern（伯尔尼大学计算机科学研究所）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）
Pengcheng Weng, Yanyu Qian, Yangxin Xu, Fei Wang
备注：
Accepted by CVPR 2026 Workshop On Any-to-Any Multimodal Learning
Robust multimodal human sensing must overcome the critical challenge of missing modalities. Two principal barriers are the Representation Gap between heterogeneous data and the Contamination Effect from low-quality modalities. These barriers are causally linked, as the corruption introduced by contamination fundamentally impedes the reduction of representation disparities. In this paper, we propose PTA, a novel "Purify-then-Align" framework that solves this causal dependency through a synergistic integration of meta-learning and knowledge diffusion. To purify the knowledge source, PTA first employs a meta-learning-driven weighting mechanism that dynamically learns to down-weight the influence of noisy, low-contributing modalities. Subsequently, to align different modalities, PTA introduces a diffusion-based knowledge distillation paradigm in which an information-rich clean teacher, formed from this purified consensus, refines the features of each student modality. The ultimate payoff of this "Purify-then-Align" strategy is the creation of exceptionally powerful single-modality encoders imbued with cross-modal knowledge. Comprehensive experiments on the large-scale MM-Fi and XRF55 datasets, under pronounced Representation Gap and Contamination Effect, demonstrate that PTA achieves state-of-the-art performance and significantly improves the robustness of single-modality models in diverse missing-modality scenarios.
The Chinese University of Hong Kong（香港中文大学）；Stanford University（斯坦福大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
Medical image annotations are prohibitively time-consuming and expensive to obtain. To alleviate annotation scarcity, many approaches have been developed to efficiently utilize extra information, e.g.,semi-supervised learning further exploring plentiful unlabeled data, domain adaptation including multi-modality learning and unsupervised domain adaptation resorting to the prior knowledge from additional modality. In this paper, we aim to investigate the feasibility of simultaneously leveraging abundant unlabeled data and well-established cross-modality data for annotation-efficient medical imag…
University of Southern California（南加州大学）；Facebook AI
To reduce a model size but retain performance, we often rely on knowledge distillation (KD) which transfers knowledge from a large "teacher" model to a smaller "student" model. However, KD on multimodal datasets such as vision-language tasks is relatively unexplored, and digesting multimodal information is challenging since different modalities present different types of information. In this paper, we perform a large-scale empirical study to investigate the importance and effects of each modality in knowledge distillation. Furthermore, we introduce a multimodal knowledge distillation framework…
Modality Disentangled Learning for Incomplete Multimodal Emotion Recognition: A Primitive Memory Distillation Perspective
Jiangsu University（江苏大学）；Griffith University（格里菲斯大学）；National University of Singapore（新加坡国立大学）；University of New South Wales（新南威尔士大学）；Fujian University of Technology（福建理工大学）；Xi’an Jiaotong-Liverpool University（西交利物浦大学）；German Research Center for Artificial Intelligence（德国人工智能研究中心）；Tsinghua University（清华大学）；Technical University of Munich（慕尼黑工业大学）；Imperial College London（伦敦帝国学院）；Queen Mary University of London（伦敦玛丽女王大学）
The Chinese University of Hong Kong（香港中文大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Stanford University（斯坦福大学）
Annotation scarcity is a long-standing problem in medical image analysis area. To efficiently leverage limited annotations, abundant unlabeled data are additionally exploited in semi-supervised learning, while well-established cross-modality data are investigated in domain adaptation. In this paper, we aim to explore the feasibility of concurrently leveraging both unlabeled data and cross-modality data for annotation-efficient cardiac segmentation. To this end, we propose a cutting-edge semi-supervised domain adaptation framework, namely Dual-Teacher++. Besides directly learning from limited l…
JDCNet: Confidence-Gated Privileged-Modality Distillation for Cost-Preserving X-ray Inference
Auckland University of Technology（奥克兰技术大学）；Guilin University of Electronic Technology（桂林电子科技大学）；Hikvision Technology Co., Ltd（海康威视技术有限公司）；Hebei University of Technology（河北工业大学）
Sun Yat-Sen University（中山大学）；DMAI Co., Ltd（DMAI有限公司）
Existing vision-based action recognition is susceptible to occlusion and appearance variations, while wearable sensors can alleviate these challenges by capturing human motion with one-dimensional time-series signal. For the same action, the knowledge learned from vision sensors and wearable sensors, may be related and complementary. However, there exists significantly large modality difference between action data captured by wearable-sensor and vision-sensor in data dimension, data distribution and inherent information content. In this paper, we propose a novel framework, named Semantics-awar…
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；Key Laboratory of Intelligent Bionic Unmanned Systems, Ministry of Education（教育部智能仿生无人系统重点实验室）；School of Artificial Intelligence, University of Science and Technology Beijing（北京科技大学人工智能学院）；School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院）
Mind the Gap: Promoting Missing Modality Brain Tumor Segmentation with Alignment
School of Robotics Xi’an Jiaotong-Liverpool University Suzhou, China；School of Advanced Technology Xi'an Jiaotong-Liverpool University Suzhou, China；School of Advanced Technology Xi’an Jiaotong-Liverpool University Suzhou, China；Data Science Research Center Duke Kunshan University Suzhou, China
Digital Medical Research Center, School of Basic Medical Science, Fudan University（复旦大学基础医学院数字医学研究中心）；Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention（上海市医学影像计算与计算机辅助干预重点实验室）
Unsupervised domain adaptation (UDA) aims to learn a model trained on source domain and performs well on unlabeled target domain. In medical image segmentation field, most existing UDA methods depend on adversarial learning to address the domain gap between different image modalities, which is ineffective due to its complicated training process. In this paper, we propose a simple yet effective UDA method based on frequency and spatial domain transfer uner multi-teacher distillation framework. In the frequency domain, we first introduce non-subsampled contourlet transform for identifying domain…
Beijing University of Posts and Telecommunications（北京邮电大学）；ByteDance（字节跳动）；USTC（中国科学技术大学）；Beijing Key Laboratory of Network System and Network Culture（北京网络系统与网络文化重点实验室）；Key Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism（文化和旅游部互动技术与体验系统重点实验室）；Zhongguancun Academy（中关村科学城）
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Massachusetts Institute of Technology（麻省理工学院）；South China University of Technology（华南理工大学）；Tsinghua University（清华大学）；Shanghai Qi Zhi Institute（上海期智研究院）
Crossmodal knowledge distillation (KD) extends traditional knowledge distillation to the area of multimodal learning and demonstrates great success in various applications. To achieve knowledge transfer across modalities, a pretrained network from one modality is adopted as the teacher to provide supervision signals to a student network learning from another modality. In contrast to the empirical success reported in prior works, the working mechanism of crossmodal KD remains a mystery. In this paper, we present a thorough understanding of crossmodal KD. We begin with two case studies and demon…
Modality-Balanced Learning for Multimedia Recommendation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Distilling Missing Modality Knowledge from Ultrasound for Endometriosis Diagnosis with Magnetic Resonance Images
Australian Institute for Machine Learning, University of Adelaide（阿德莱德大学澳大利亚机器学习研究所）；Flinders Health and Medical Research Institute, Flinders University（弗林德斯大学弗林德斯健康与医学研究所）；Robinson Research Institute, University of Adelaide（阿德莱德大学罗宾逊研究所）；Centre for Vision, Speech and Signal Processing, University of Surrey（萨里大学视觉、语音与信号处理中心）
Shanghai Jiao Tong University（上海交通大学）；Télécom Paris（巴黎电信学院）；Institut Polytechnique de Paris（巴黎理工学院）
The joint use of multiple imaging modalities for medical image segmentation has been widely studied in recent years. The fusion of information from different modalities has demonstrated to improve the segmentation accuracy, with respect to mono-modal segmentations, in several applications. However, acquiring multiple modalities is usually not possible in a clinical setting due to a limited number of physicians and scanners, and to limit costs and scan time. Most of the time, only one modality is acquired. In this paper, we propose KD-Net, a framework to transfer knowledge from a trained multi-…
GaitKD: A Universal Decoupled Distillation Framework for Efficient Gait Recognition
The City University of New York（纽约城市大学）；Wuhan University（武汉大学）；Beijing Jiaotong University（北京交通大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Oulu（奥卢大学）
SCKD: Semi-Supervised Cross-Modality Knowledge Distillation for 4D Radar Object Detection
Zhejiang University（浙江大学）；Zhejiang Provincial Key Laboratory of Multi-Modal Communication Networks and Intelligent Information Processing（浙江省多模态通信网络与智能信息处理重点实验室）；China North Artificial Intelligence & Innovation Research Institude（北方人工智能创新研究院）
Texas State University（德克萨斯州立大学）；Illinois Institute of Technology（伊利诺伊理工学院）
Wearable sensor-based Human Action Recognition (HAR) has achieved remarkable success recently. However, the accuracy performance of wearable sensor-based HAR is still far behind the ones from the visual modalities-based system (i.e., RGB video, skeleton, and depth). Diverse input modalities can provide complementary cues and thus improve the accuracy performance of HAR, but how to take advantage of multi-modal data on wearable sensor-based HAR has rarely been explored. Currently, wearable devices, i.e., smartwatches, can only capture limited kinds of non-visual modality data. This hinders the …
RGB-Infrared (RGB-IR) person re-identification (ReID) is a technology where the system can automatically identify the same person appearing at different parts of a video when light is unavailable. The critical challenge of this task is the cross-modality gap of features under different modalities. To solve this challenge, we proposed a Teacher-Student GAN model (TS-GAN) to adopt different domains and guide the ReID backbone to learn better ReID information. (1) In order to get corresponding RGB-IR image pairs, the RGB-IR Generative Adversarial Network (GAN) was used to generate IR images. (2) …
Event cameras sense per-pixel intensity changes and produce asynchronous event streams with high dynamic range and less motion blur, showing advantages over conventional cameras. A hurdle of training event-based models is the lack of large qualitative labeled data. Prior works learning end-tasks mostly rely on labeled or pseudo-labeled datasets obtained from the active pixel sensor (APS) frames; however, such datasets' quality is far from rivaling those based on the canonical images. In this paper, we propose a novel approach, called \textbf{EvDistill}, to learn a student network on the unlabe…
Northwestern Polytechnical University（西北工业大学）；Air Force Engineering University（空军工程大学）；wrnch（wrnch公司）；Nanchang University（南昌大学）
The target representation learned by convolutional neural networks plays an important role in Thermal Infrared (TIR) tracking. Currently, most of the top-performing TIR trackers are still employing representations learned by the model trained on the RGB data. However, this representation does not take into account the information in the TIR modality itself, limiting the performance of TIR tracking. To solve this problem, we propose to distill representations of the TIR modality from the RGB modality with Cross-Modal Distillation (CMD) on a large amount of unlabeled paired RGB-TIR data. We take…
Unsupervised Tumor-Aware Distillation for Multi-Modal Brain Image Translation
School of Computer Science and Engineering, South China University of Technology（华南理工大学计算机科学与工程学院）；Golisano College of Computing and Information Sciences, Rochester Institute of Technology（罗切斯特理工大学戈利萨诺计算与信息科学学院）
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Google Research（谷歌研究院）
Often we wish to transfer representational knowledge from one neural network to another. Examples include distilling a large network into a smaller one, transferring knowledge from one sensory modality to a second, or ensembling a collection of models into a single estimator. Knowledge distillation, the standard approach to these problems, minimizes the KL divergence between the probabilistic outputs of a teacher and student network. We demonstrate that this objective ignores important structural knowledge of the teacher network. This motivates an alternative objective by which we train a stud…
Memorial Sloan Kettering Cancer Center（纪念斯隆·凯特琳癌症中心）
Despite the widespread availability of in-treatment room cone beam computed tomography (CBCT) imaging, due to the lack of reliable segmentation methods, CBCT is only used for gross set up corrections in lung radiotherapies. Accurate and reliable auto-segmentation tools could potentiate volumetric response assessment and geometry-guided adaptive radiation therapies. Therefore, we developed a new deep learning CBCT lung tumor segmentation method. Methods: The key idea of our approach called cross modality educed distillation (CMEDL) is to use magnetic resonance imaging (MRI) to guide a CBCT segm…
Purify then Guide: Rethinking Domain Generalization for Multimodal Face Anti-Spoofing
College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）；School of Computing and Information Technology, Great Bay University（大湾区大学计算与信息科技学院）；Dongguan Key Laboratory for Intelligence and Information Technology（东莞智能与信息处理重点实验室）；Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen University（广东省智能信息处理重点实验室）；Tencent Youtu Lab（腾讯优图实验室）；School of Psychology, Shanghai Jiao Tong University（上海交通大学心理学院）；Faculty of Applied Sciences, Macao Polytechnic University（澳门理工学院应用科学学院）；The Chinese University of Hong Kong（香港中文大学）
In this work, we address the issues of missing modalities that have arisen from the Visual Question Answer-Difference prediction task and find a novel method to solve the task at hand. We address the missing modality-the ground truth answers-that are not present at test time and use a privileged knowledge distillation scheme to deal with the issue of the missing modality. In order to efficiently do so, we first introduce a model, the "Big" Teacher, that takes the image/question/answer triplet as its input and outperforms the baseline, then use a combination of models to distill knowledge to a …
This paper strives for action recognition and detection in video modalities like RGB, depth maps or 3D-skeleton sequences when only limited modality-specific labeled examples are available. For the RGB, and derived optical-flow, modality many large-scale labeled datasets have been made available. They have become the de facto pre-training choice when recognizing or detecting new actions from RGB datasets that have limited amounts of labeled examples available. Unfortunately, large-scale labeled action datasets for other modalities are unavailable for pre-training. In this paper, our goal is to…
Lightweight Facial Landmark Detection in Thermal Images via Multi-Level Cross-Modal Knowledge Transfer
Human-Robot Interfaces and Interaction Laboratory, Istituto Italiano di Tecnologia, Genoa, Italy（人机交互实验室，意大利技术研究院，热那亚，意大利）；Ph.D. Program of National Interest in Robotics and Intelligent Machines (DRIM), Università di Genova（机器人与智能机器国家利益博士项目，热那亚大学）
