MINIMA: Modality Invariant Image Matching

2024-12-27

AI Summary

Cross-view and cross-modal image matching suffers from poor generalization due to large imaging discrepancies and scarcity of accurate ground-truth annotations. To address this, we propose MINIMA, a unified matching framework introducing a novel generative data augmentation paradigm: leveraging Stable Diffusion–based models, we construct MD-syn—the first synthetic dataset covering 19 cross-modal combinations with precise pixel-level correspondence labels—eliminating reliance on modality-specific designs and real-world annotations. MINIMA features an end-to-end, plug-and-play architecture that jointly integrates cross-modal contrastive learning and label inheritance. Experiments demonstrate that MINIMA consistently outperforms state-of-the-art methods across all 19 cross-modal tasks and maintains superior performance in zero-shot settings. Both the code and the MD-syn dataset are publicly released to advance foundational research in multimodal perception.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Image matching for both cross-view and cross-modality plays a critical role in multimodal perception. In practice, the modality gap caused by different imaging systems/styles poses great challenges to the matching task. Existing works try to extract invariant features for specific modalities and train on limited datasets, showing poor generalization. In this paper, we present MINIMA, a unified image matching framework for multiple cross-modal cases. Without pursuing fancy modules, our MINIMA aims to enhance universal performance from the perspective of data scaling up. For such purpose, we propose a simple yet effective data engine that can freely produce a large dataset containing multiple modalities, rich scenarios, and accurate matching labels. Specifically, we scale up the modalities from cheap but rich RGB-only matching data, by means of generative models. Under this setting, the matching labels and rich diversity of the RGB dataset are well inherited by the generated multimodal data. Benefiting from this, we construct MD-syn, a new comprehensive dataset that fills the data gap for general multimodal image matching. With MD-syn, we can directly train any advanced matching pipeline on randomly selected modality pairs to obtain cross-modal ability. Extensive experiments on in-domain and zero-shot matching tasks, including $19$ cross-modal cases, demonstrate that our MINIMA can significantly outperform the baselines and even surpass modality-specific methods. The dataset and code are available at https://github.com/LSXI7/MINIMA .

Problem

• Multi-type Image Matching
• Feature Learning
• Adaptability

Innovation

• MINIMA
• Multi-Type Image Matching
• Data Generation