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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wei, Rukai, Cui, Heng, Liu, Yu, Hou, Yufeng, Xie, Yanzhao, Zhou, Ke
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910563068542976
author Wei, Rukai
Cui, Heng
Liu, Yu
Hou, Yufeng
Xie, Yanzhao
Zhou, Ke
author_facet Wei, Rukai
Cui, Heng
Liu, Yu
Hou, Yufeng
Xie, Yanzhao
Zhou, Ke
contents 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 capture latent multi-modal semantics and effectively bridge the modality gap between 2D and 3D. To address these issues without relying on hand-crafted labels, we propose contrastive masked autoencoders based self-supervised hashing (CMAH) for retrieval between images and point-cloud data. We start by contrasting 2D-3D pairs and explicitly constraining them into a joint Hamming space. This contrastive learning process ensures robust discriminability for the generated hash codes and effectively reduces the modality gap. Moreover, we utilize multi-modal auto-encoders to enhance the model's understanding of multi-modal semantics. By completing the masked image/point-cloud data modeling task, the model is encouraged to capture more localized clues. In addition, the proposed multi-modal fusion block facilitates fine-grained interactions among different modalities. Extensive experiments on three public datasets demonstrate that the proposed CMAH significantly outperforms all baseline methods.
format Preprint
id arxiv_https___arxiv_org_abs_2408_05711
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Contrastive masked auto-encoders based self-supervised hashing for 2D image and 3D point cloud cross-modal retrieval
Wei, Rukai
Cui, Heng
Liu, Yu
Hou, Yufeng
Xie, Yanzhao
Zhou, Ke
Computer Vision and Pattern Recognition
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 capture latent multi-modal semantics and effectively bridge the modality gap between 2D and 3D. To address these issues without relying on hand-crafted labels, we propose contrastive masked autoencoders based self-supervised hashing (CMAH) for retrieval between images and point-cloud data. We start by contrasting 2D-3D pairs and explicitly constraining them into a joint Hamming space. This contrastive learning process ensures robust discriminability for the generated hash codes and effectively reduces the modality gap. Moreover, we utilize multi-modal auto-encoders to enhance the model's understanding of multi-modal semantics. By completing the masked image/point-cloud data modeling task, the model is encouraged to capture more localized clues. In addition, the proposed multi-modal fusion block facilitates fine-grained interactions among different modalities. Extensive experiments on three public datasets demonstrate that the proposed CMAH significantly outperforms all baseline methods.
title Contrastive masked auto-encoders based self-supervised hashing for 2D image and 3D point cloud cross-modal retrieval
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.05711