paper-with-me

홈 › Papers

ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval

2025-11-02 · Ahmed Masry, Megh Thakkar, Patrice Bechard, Sathwik Tejaswi Madhusudhan, Rabiul Awal, Shambhavi Mishra, Akshay Kalkunte Suresh, Srivatsava Daruru, Enamul Hoque, Spandana Gella, Torsten Scholak, Sai Rajeswar arxiv

Retrieval-augmented generation has proven practical when models require specialized knowledge or access to the latest data. However, existing methods for multimodal document retrieval often replicate techniques developed for text-only retrieval, whether in how they encode documents, define training objectives, or compute similarity scores. To address these limitations, we present ColMate, a document retrieval model that bridges the gap between multimodal representation learning and document retrieval. ColMate utilizes a novel OCR-based pretraining objective, a self-supervised masked contrastive learning objective, and a late interaction scoring mechanism more relevant to multimodal document structures and visual characteristics. ColMate obtains 3.61% improvements over existing retrieval models on the ViDoRe V2 benchmark, demonstrating stronger generalization to out-of-domain benchmarks.

📄 PDF Abstract BibTeX arXiv:2511.00903

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningContrastive Learning

Similar Papers 제목 키워드 기반

MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining

2022-08-25 · CVPR 2023 1 · Xiaoyi Dong, Jianmin Bao, Yinglin Zheng, Ting Zhang 외

This paper presents a simple yet effective framework MaskCLIP, which incorporates a newly proposed masked self-distillation into contrastive language-image pretraining. The core idea of masked self-distillation is to dis…

Representation Learning

SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment

2024-01-04 · Ziping Ma, Furong Xu, Jian Liu, Ming Yang 외

Multimodal alignment between language and vision is the fundamental topic in current vision-language model research. Contrastive Captioners (CoCa), as a representative method, integrates Contrastive Language-Image Pretra…

Image Captioningimage-classificationImage ClassificationImage Reconstruction+7

MMCLIP: Cross-modal Attention Masked Modelling for Medical Language-Image Pre-Training

2024-07-28 · Biao Wu, Yutong Xie, Zeyu Zhang, Minh Hieu Phan 외

Vision-and-language pretraining (VLP) in the medical field utilizes contrastive learning on image-text pairs to achieve effective transfer across tasks. Yet, current VLP approaches with the masked modeling strategy face …

Contrastive LearningLanguage ModelingLanguage ModellingMasked Language Modeling

Contrastive masked auto-encoders based self-supervised hashing for 2D image and 3D point cloud cross-modal retrieval

2024-08-11 · Rukai Wei, Heng Cui, Yu Liu, Yufeng Hou 외

Implementing cross-modal hashing between 2D images and 3D point-cloud data is a growing concern in real-world retrieval systems. Simply applying existing cross-modal approaches to this new task fails to adequately captur…

Contrastive LearningCross-Modal RetrievalRetrieval

Learning Representations for Clustering via Partial Information Discrimination and Cross-Level Interaction

2024-01-24 · Hai-Xin Zhang, Dong Huang, Hua-Bao Ling, Guang-Yu Zhang 외

In this paper, we present a novel deep image clustering approach termed PICI, which enforces the partial information discrimination and the cross-level interaction in a joint learning framework. In particular, we leverag…

ClusteringContrastive LearningDeep ClusteringImage Clustering+2