Cross-modal knowledge distillation (CMKD) refers to the scenario in which a learning framework must handle training and test data that exhibit a modality mismatch, more precisely, training and test data do not cover the same set of data modalities. Traditional approaches for CMKD are based on a teacher/student paradigm where a teacher is trained on multi-modal data with the aim to successively distill knowledge from a multi-modal teacher to a single-modal student. Despite the widespread adoption of such paradigm, recent research has highlighted its inherent limitations in the context of cross-modal knowledge transfer.Taking a step beyond the teacher/student paradigm, here we introduce a new framework for cross-modal knowledge distillation, named DisCoM-KD (Disentanglement-learning based Cross-Modal Knowledge Distillation), that explicitly models different types of per-modality information with the aim to transfer knowledge from multi-modal data to a single-modal classifier. To this end, DisCoM-KD effectively combines disentanglement representation learning with adversarial domain adaptation to simultaneously extract, foreach modality, domain-invariant, domain-informative and domain-irrelevant features according to a specific downstream task. Unlike the traditional teacher/student paradigm, our framework simultaneously learns all single-modal classifiers, eliminating the need to learn each student model separately as well as the teacher classifier. We evaluated DisCoM-KD on three standard multi-modal benchmarks and compared its behaviourwith recent SOTA knowledge distillation frameworks. The findings clearly demonstrate the effectiveness of DisCoM-KD over competitors considering mismatch scenarios involving both overlapping and non-overlapping modalities. These results offer insights to reconsider the traditional paradigm for distilling information from multi-modal data to single-modal neural networks.
Integrating low-power wearable Internet of Things (IoT) systems into routine health monitoring is an ongoing challenge. Recent advances in the computation capabilities of wearables make it possible to target complex scenarios by exploiting multiple biosignals and using high-performance algorithms, such as Deep Neural Networks (DNNs). There is, however, a trade-off between performance of the algorithms and the low-power requirements of IoT platforms with limited resources. Besides, physically larger and multi-biosignal-based wearables bring significant discomfort to the patients. Consequently, …
University of Moratuwa（莫拉图瓦大学）；Harvard University（哈佛大学）；Aarhus University（奥胡斯大学）；Florida International University（佛罗里达国际大学）
Sleep plays a crucial role in the well-being of human lives. Traditional sleep studies using Polysomnography are associated with discomfort and often lower sleep quality caused by the acquisition setup. Previous works have focused on developing less obtrusive methods to conduct high-quality sleep studies, and ear-EEG is among popular alternatives. However, the performance of sleep staging based on ear-EEG is still inferior to scalp-EEG based sleep staging. In order to address the performance gap between scalp-EEG and ear-EEG based sleep staging, we propose a cross-modal knowledge distillation …
Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）
Stock trend forecasting has become a popular research direction that attracts widespread attention in the financial field. Though deep learning methods have achieved promising results, there are still many limitations, for example, how to extract clean features from the raw stock data. In this paper, we introduce an \emph{Augmented Disentanglement Distillation (ADD)} approach to remove interferential features from the noised raw data. Specifically, we present 1) a disentanglement structure to separate excess and market information from the stock data to avoid the two factors disturbing each ot…
It is challenging to disentangle an object into two orthogonal spaces of content and style since each can influence the visual observation differently and unpredictably. It is rare for one to have access to a large number of data to help separate the influences. In this paper, we present a novel framework to learn this disentangled representation in a completely unsupervised manner. We address this problem in a two-branch Autoencoder framework. For the structural content branch, we project the latent factor into a soft structured point tensor and constrain it with losses derived from prior kno…
Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities
Academy for Engineering and Technology, Fudan University（复旦大学工程技术学院）；Jilin Provincial Key Laboratory of Intelligence Science and Engineering（吉林省智能科学与工程重点实验室）；Engineering Research Center of AI and Robotics, Ministry of Education（教育部人工智能与机器人工程研究中心）
Shenzhen University of Advanced Technology（深圳先进技术大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Xi’an Jiaotong University（西安交通大学）
Closed-Loop Unsupervised Representation Disentanglement with $β$-VAE Distillation and Diffusion Probabilistic Feedback
Ningbo Institute of Digital Twin, Eastern Institute of Technology（宁波数字孪生研究所、东部技术研究所）；Shanghai Jiao Tong University（上海交通大学）；Xi’an Jiaotong University（西安交通大学）
Rapid Bone Scintigraphy Enhancement via Semantic Prior Distillation from Segment Anything Model
Department of Nuclear Medicine, Shanghai Children’s Hospital, School of Medicine, Shanghai Jiao Tong University（核医学科，上海儿童医学中心，上海交通大学医学院）；School of Microelectronics, Shanghai University（微电子学院，上海大学）；Department of Ophthalmology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine（眼科，瑞金医院，上海交通大学医学院）；Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology（电子与计算机工程系，香港科学与技术大学）；School of Software Engineering, Sun Yat-sen University（软件工程学院，中山大学）；College of Computer Science and Electronic Engineering, Hunan University（计算机科学与电子工程学院，湖南大学）；School of Computer Science and Technology, Henan Polytechnic University（计算机科学与技术学院，河南理工大学）
本文首次将 SAM 语义先验引入医学图像恢复，通过级联网络和三个语义模块增强儿科快速骨闪烁显像，并构建首个专用数据集 RBS，在多项指标上优于现有方法。
University of Southern California（南加州大学）；USC Institute for Creative Technologies（南加州大学创意技术研究所）；Snap Inc.（阅后即焚公司）
Disentangling data into interpretable and independent factors is critical for controllable generation tasks. With the availability of labeled data, supervision can help enforce the separation of specific factors as expected. However, it is often expensive or even impossible to label every single factor to achieve fully-supervised disentanglement. In this paper, we adopt a general setting where all factors that are hard to label or identify are encapsulated as a single unknown factor. Under this setting, we propose a flexible weakly-supervised multi-factor disentanglement framework DisUnknown, …
Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning
MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University（上海交通大学人工智能研究院教育部人工智能重点实验室）；Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China（东方理工高等研究院宁波数字孪生研究院）；Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Ningbo, China（宁波市空间智能与数字衍生重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Shenyang Institute of Computing Technology, Chinese Academy of Sciences（中国科学院沈阳计算技术研究所）；Shenyang CASNC Technology Co., Ltd（沈阳中科数控技术股份有限公司）
Robust Multimodal Learning for Ophthalmic Disease Grading via Disentangled Representation
MBZUAI, United Arab Emirates（MBZUAI，阿联酋）；Monash University, Australia（墨尔本大学，澳大利亚）；Liverpool University, United Kingdom（利物浦大学，英国）；China Unicom (Shanghai) Industrial Internet Co., Ltd., China（中国联合（上海）工业互联网有限公司，中国）；Shanghai AI Lab, China（上海人工智能实验室，中国）
Bar Ilan University（巴伊兰大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Contextualized word representations, such as ELMo and BERT, were shown to perform well on various semantic and syntactic tasks. In this work, we tackle the task of unsupervised disentanglement between semantics and structure in neural language representations: we aim to learn a transformation of the contextualized vectors, that discards the lexical semantics, but keeps the structural information. To this end, we automatically generate groups of sentences which are structurally similar but semantically different, and use metric-learning approach to learn a transformation that emphasizes the str…
