{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/stil-semi-supervised-tabular-image-learning","title":"STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classification","arxiv_id":"2503.06277","date":"2025-03-08","proceeding":"CVPR 2025 1","authors":["Siyi Du","Xinzhe Luo","Declan P. O'Regan","Chen Qin"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2503.06277v1","url_pdf":"https://arxiv.org/pdf/2503.06277v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"stil-semi-supervised-tabular-image-learning","repo_url":"https://github.com/siyi-wind/STiL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.06277","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}