paper-with-me

홈 › Papers

Cross-Modality Sub-Image Retrieval using Contrastive Multimodal Image Representations

2022-01-10 · Eva Breznik, Elisabeth Wetzer, Joakim Lindblad, Nataša Sladoje

In tissue characterization and cancer diagnostics, multimodal imaging has emerged as a powerful technique. Thanks to computational advances, large datasets can be exploited to discover patterns in pathologies and improve diagnosis. However, this requires efficient and scalable image retrieval methods. Cross-modality image retrieval is particularly challenging, since images of similar (or even the same) content captured by different modalities might share few common structures. We propose a new application-independent content-based image retrieval (CBIR) system for reverse (sub-)image search across modalities, which combines deep learning to generate representations (embedding the different modalities in a common space) with classical feature extraction and bag-of-words models for efficient and reliable retrieval. We illustrate its advantages through a replacement study, exploring a number of feature extractors and learned representations, as well as through comparison to recent (cross-modality) CBIR methods. For the task of (sub-)image retrieval on a (publicly available) dataset of brightfield and second harmonic generation microscopy images, the results show that our approach is superior to all tested alternatives. We discuss the shortcomings of the compared methods and observe the importance of equivariance and invariance properties of the learned representations and feature extractors in the CBIR pipeline. Code is available at: \url{https://github.com/MIDA-group/CrossModal_ImgRetrieval}.

📄 PDF Abstract BibTeX arXiv:2201.03597

Code (1)

mida-group/crossmodal_imgretrieval 공식 구현 pytorch

Tasks

Content-Based Image RetrievalImage RetrievalRetrieval

Similar Papers 제목 키워드 기반

Generalized Contrastive Learning for Universal Multimodal Retrieval

2025-09-30 · Jungsoo Lee, Janghoon Cho, Hyojin Park, Munawar Hayat 외 arxiv

Despite their consistent performance improvements, cross-modal retrieval models (e.g., CLIP) show degraded performances with retrieving keys composed of fused image-text modality (e.g., Wikipedia pages with both images a…

Cross-Modal RetrievalContrastive Learning

MCA: Modality Composition Awareness for Robust Composed Multimodal Retrieval

2025-10-17 · Qiyu Wu, Shuyang Cui, Satoshi Hayakawa, Wei-Yao Wang 외 arxiv

Multimodal retrieval, which seeks to retrieve relevant content across modalities such as text or image, supports applications from AI search to contents production. Despite the success of separate-encoder approaches like…

Contrastive Learning

Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning

2024-12-10 · Can Yaras, Siyi Chen, Peng Wang, Qing Qu

Multimodal learning has recently gained significant popularity, demonstrating impressive performance across various zero-shot classification tasks and a range of perceptive and generative applications. Models such as Con…

Contrastive LearningImage-text RetrievalSchedulingText Retrieval+2

The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment

2025-11-26 · Stefanos Koutoupis, Michaela Areti Zervou, Konstantinos Kontras, Maarten De Vos 외 arxiv

Learning joint representations across multiple modalities remains a central challenge in multimodal machine learning. Prevailing approaches predominantly operate in pairwise settings, aligning two modalities at a time. W…

Hidden in the Multiplicative Interaction: Uncovering Fragility in Multimodal Contrastive Learning

2026-04-07 · Tillmann Rheude, Stefan Hegselmann, Roland Eils, Benjamin Wild arxiv

Contrastive learning has become a standard approach for unsupervised learning from paired data, as demonstrated by CLIP for image-text matching. However, many domains involve more than two modalities and require objectiv…

Cross-Modal RetrievalContrastive LearningImage-text matching