Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Xun, Gu, Yufan, Hu, Disen, Hou, Yuqing, Yao, Yazhou, Shen, Fumin, Shen, Heng Tao, Xu, Xing
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917462255075328
author Jiang, Xun
Gu, Yufan
Hu, Disen
Hou, Yuqing
Yao, Yazhou
Shen, Fumin
Shen, Heng Tao
Xu, Xing
author_facet Jiang, Xun
Gu, Yufan
Hu, Disen
Hou, Yuqing
Yao, Yazhou
Shen, Fumin
Shen, Heng Tao
Xu, Xing
contents Multimodal learning often grapples with the challenge of low-quality data, which predominantly manifests as two facets: modality imbalance and noisy corruption. While these issues are often studied in isolation, we argue that they share a common root in the predictive uncertainty towards the reliability of individual modalities and instances during learning. In this paper, we propose a unified framework, termed Conformal Predictive Self-Calibration (CPSC), which leverages conformal prediction to equip the model with the ability to perform self-guided calibration on-the-fly. The core of our proposed CPSC lies in a novel self-calibrating training loop that seamlessly integrates two key modules: (1) Representation Self-Calibration, which decomposes unimodal features into components, and selectively fuses the most robust ones identified by a conformal predictor to enhance feature resilience. (2) Gradient Self-Calibration, which recalibrates the gradient flow during backpropagation based on instance-wise reliability scores, steering the optimization towards more trustworthy directions. Furthermore, we also devise a self-update strategy for the conformal predictor to ensure the entire system co-evolves consistently throughout the training process. Extensive experiments on six benchmark datasets under both imbalanced and noisy settings demonstrate that our CPSC framework consistently outperforms existing state-of-the-art methods. Our code is available at https://github.com/XunCHN/CPSC.
format Preprint
id arxiv_https___arxiv_org_abs_2605_03820
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration
Jiang, Xun
Gu, Yufan
Hu, Disen
Hou, Yuqing
Yao, Yazhou
Shen, Fumin
Shen, Heng Tao
Xu, Xing
Computer Vision and Pattern Recognition
Machine Learning
Multimedia
Multimodal learning often grapples with the challenge of low-quality data, which predominantly manifests as two facets: modality imbalance and noisy corruption. While these issues are often studied in isolation, we argue that they share a common root in the predictive uncertainty towards the reliability of individual modalities and instances during learning. In this paper, we propose a unified framework, termed Conformal Predictive Self-Calibration (CPSC), which leverages conformal prediction to equip the model with the ability to perform self-guided calibration on-the-fly. The core of our proposed CPSC lies in a novel self-calibrating training loop that seamlessly integrates two key modules: (1) Representation Self-Calibration, which decomposes unimodal features into components, and selectively fuses the most robust ones identified by a conformal predictor to enhance feature resilience. (2) Gradient Self-Calibration, which recalibrates the gradient flow during backpropagation based on instance-wise reliability scores, steering the optimization towards more trustworthy directions. Furthermore, we also devise a self-update strategy for the conformal predictor to ensure the entire system co-evolves consistently throughout the training process. Extensive experiments on six benchmark datasets under both imbalanced and noisy settings demonstrate that our CPSC framework consistently outperforms existing state-of-the-art methods. Our code is available at https://github.com/XunCHN/CPSC.
title Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration
topic Computer Vision and Pattern Recognition
Machine Learning
Multimedia
url https://arxiv.org/abs/2605.03820