English
Related papers

Related papers: Quantifying Modality Contributions via Disentangli…

200 papers

Knowledge distillation deploys complex machine learning models in resource-constrained environments by training a smaller student model to emulate internal representations of a complex teacher model. However, the teacher's representations…

Addressing missing modalities presents a critical challenge in multimodal learning. Current approaches focus on developing models that can handle modality-incomplete inputs during inference, assuming that the full set of modalities are…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Yunpeng Zhao , Cheng Chen , Qing You Pang , Quanzheng Li , Carol Tang , Beng-Ti Ang , Yueming Jin

Multimodal AI models have achieved impressive performance in tasks that require integrating information from multiple modalities, such as vision and language. However, their "black-box" nature poses a major barrier to deployment in…

Artificial Intelligence · Computer Science 2026-02-18 Zhanliang Wang , Kai Wang

This paper introduces a novel information-theoretic perspective on the relationship between prominent group fairness notions in machine learning, namely statistical parity, equalized odds, and predictive parity. It is well known that…

Information Theory · Computer Science 2024-10-25 Faisal Hamman , Sanghamitra Dutta

Multi-modal MRIs are widely used in neuroimaging applications since different MR sequences provide complementary information about brain structures. Recent works have suggested that multi-modal deep learning analysis can benefit from…

Computer Vision and Pattern Recognition · Computer Science 2021-06-14 Jiahong Ouyang , Ehsan Adeli , Kilian M. Pohl , Qingyu Zhao , Greg Zaharchuk

We investigate the partial information decomposition (PID) framework as a tool for edge nomination. We consider both the $I_{\cap}^{\text{min}}$ and $I_{\cap}^{\text{PM}}$ PIDs, from arXiv:1004.2515 and arXiv:1801.09010 respectively, and we…

Information Theory · Computer Science 2021-12-24 Jesse Milzman , Vince Lyzinski

A core task in multi-modal learning is to integrate information from multiple feature spaces (e.g., text and audio), offering modality-invariant essential representations of data. Recent research showed that, classical tools such as {\it…

Machine Learning · Computer Science 2024-10-02 Subash Timilsina , Sagar Shrestha , Xiao Fu

Recent advances in representation learning have demonstrated an ability to represent information from different modalities such as video, text, and audio in a single high-level embedding vector. In this work we present a self-supervised…

Computer Vision and Pattern Recognition · Computer Science 2021-06-11 Alexander H. Liu , SouYoung Jin , Cheng-I Jeff Lai , Andrew Rouditchenko , Aude Oliva , James Glass

Concept-based approaches, which aim to identify human-understandable concepts within a model's internal representations, are a promising method for interpreting embeddings from deep neural network models, such as CLIP. While these…

Machine Learning · Computer Science 2025-06-18 Jitian Zhao , Chenghui Li , Frederic Sala , Karl Rohe

Partial information decomposition (PID) partitions the information that a set of sources has about a target variable into synergistic, unique, and redundant contributions. This information-theoretic tool has recently attracted attention due…

Information Theory · Computer Science 2020-10-15 Abdullah Makkeh , Dirk Oliver Theis , Raul Vicente

In order to perform multimodal fusion of heterogeneous signals, we need to understand their interactions: how each modality individually provides information useful for a task and how this information changes in the presence of other…

Machine Learning · Computer Science 2023-11-01 Paul Pu Liang , Yun Cheng , Ruslan Salakhutdinov , Louis-Philippe Morency

Medical multimodal representation learning aims to integrate heterogeneous clinical data into unified patient representations to support predictive modeling, which remains an essential yet challenging task in the medical data mining…

Machine Learning · Computer Science 2025-09-09 Xiaoguang Zhu , Lianlong Sun , Yang Liu , Pengyi Jiang , Uma Srivatsa , Nipavan Chiamvimonvat , Vladimir Filkov

Multimodal human action understanding is a significant problem in computer vision, with the central challenge being the effective utilization of the complementarity among diverse modalities while maintaining model efficiency. However, most…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Hongsong Wang , Heng Fei , Bingxuan Dai , Jie Gui

To enhance the interpretability of multimodal unified representations, many studies have focused on discrete unified representations. These efforts typically start with contrastive learning and gradually extend to the disentanglement of…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Hai Huang , Yan Xia , Shengpeng Ji , Shulei Wang , Hanting Wang , Minghui Fang , Jieming Zhu , Zhenhua Dong , Sashuai Zhou , Zhou Zhao

Real-world problems are often dependent on multiple data modalities, making multimodal fusion essential for leveraging diverse information sources. In high-stakes domains, such as in healthcare, understanding how each modality contributes…

Neural and Evolutionary Computing · Computer Science 2025-05-19 Mafalda Malafaia , Thalea Schlender , Tanja Alderliesten , Peter A. N. Bosman

We present modality gap, an intriguing geometric phenomenon of the representation space of multi-modal models. Specifically, we show that different data modalities (e.g. images and text) are embedded at arm's length in their shared…

Computation and Language · Computer Science 2022-10-21 Weixin Liang , Yuhui Zhang , Yongchan Kwon , Serena Yeung , James Zou

Multimodal models often converge to a dominant-modality solution, in which a stronger, faster-converging modality overshadows weaker ones. This modality imbalance causes suboptimal performance. Existing methods attempt to balance different…

Multimedia · Computer Science 2026-03-19 Zechang Xiong , Da Li , Kexin Tang , Pengyuan Li , Wenkang Kong , Yulan Hu

Research on multi-modal learning dominantly aligns the modalities in a unified space at training, and only a single one is taken for prediction at inference. However, for a real machine, e.g., a robot, sensors could be added or removed at…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Yuanhuiyi Lyu , Xu Zheng , Dahun Kim , Lin Wang

Multimodal learning enables neural networks to integrate information from heterogeneous sources, but active learning in this setting faces distinct challenges. These include missing modalities, differences in modality difficulty, and…

Machine Learning · Computer Science 2026-04-01 Dustin Eisenhardt , Yunhee Jeong , Florian Buettner

Spuriousness arises when there is an association between two or more variables in a dataset that are not causally related. In this work, we propose an explainability framework to preemptively disentangle the nature of such spurious…

Machine Learning · Computer Science 2025-11-17 Barproda Halder , Faisal Hamman , Pasan Dissanayake , Qiuyi Zhang , Ilia Sucholutsky , Sanghamitra Dutta