paper-with-me

Papers

STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classification

2025-03-08 · CVPR 2025 1 · Siyi Du, Xinzhe Luo, Declan P. O'Regan, Chen Qin

Multimodal image-tabular learning is gaining attention, yet it faces challenges due to limited labeled data. While earlier work has applied self-supervised learning (SSL) to unlabeled data, its task-agnostic nature often results in learning suboptimal features for downstream tasks. Semi-supervised learning (SemiSL), which combines labeled and unlabeled data, offers a promising solution. However, existing multimodal SemiSL methods typically focus on unimodal or modality-shared features, ignoring valuable task-relevant modality-specific information, leading to a Modality Information Gap. In this paper, we propose STiL, a novel SemiSL tabular-image framework that addresses this gap by comprehensively exploring task-relevant information. STiL features a new disentangled contrastive consistency module to learn cross-modal invariant representations of shared information while retaining modality-specific information via disentanglement. We also propose a novel consensus-guided pseudo-labeling strategy to generate reliable pseudo-labels based on classifier consensus, along with a new prototype-guided label smoothing technique to refine pseudo-label quality with prototype embeddings, thereby enhancing task-relevant information learning in unlabeled data. Experiments on natural and medical image datasets show that STiL outperforms the state-of-the-art supervised/SSL/SemiSL image/multimodal approaches. Our code is publicly available.

📄 PDF Abstract BibTeX arXiv:2503.06277

Code (1)

siyi-wind/STiL 공식 구현 pytorch

Tasks

DisentanglementPseudo LabelSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Progressive Feature Upgrade in Semi-supervised Learning on Tabular Domain

2022-12-01 · Morteza Mohammady Gharasuie, Fenjiao Wang

Recent semi-supervised and self-supervised methods have shown great success in the image and text domain by utilizing augmentation techniques. Despite such success, it is not easy to transfer this success to tabular doma…

VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain

2020-12-01 · NeurIPS 2020 12 · Jinsung Yoon, Yao Zhang, James Jordon, Mihaela van der Schaar

Self- and semi-supervised learning frameworks have made significant progress in training machine learning models with limited labeled data in image and language domains. These methods heavily rely on the unique structure…

Data AugmentationImputationSelf-Supervised Learning

Geodesic Flow Kernels for Semi-Supervised Learning on Mixed-Variable Tabular Dataset

2024-12-17 · Yoontae Hwang, YongJae lee

Tabular data poses unique challenges due to its heterogeneous nature, combining both continuous and categorical variables. Existing approaches often struggle to effectively capture the underlying structure and relationsh…

Contrastive Mixup: Self- and Semi-Supervised learning for Tabular Domain

2021-08-27 · Sajad Darabi, Shayan Fazeli, Ali Pazoki, Sriram Sankararaman 외

Recent literature in self-supervised has demonstrated significant progress in closing the gap between supervised and unsupervised methods in the image and text domains. These methods rely on domain-specific augmentations…

ICLAD: In-Context Learning for Unified Tabular Anomaly Detection Across Supervision Regimes

2026-03-19 · Jack Yi Wei, Narges Armanfard arxiv

Anomaly detection on tabular data is commonly studied under three supervision regimes, including one-class settings that assume access to anomaly-free training samples, fully unsupervised settings with unlabeled and pote…

Anomaly Detection