paper-with-me

홈 › Papers

Mx2M: Masked Cross-Modality Modeling in Domain Adaptation for 3D Semantic Segmentation

2023-07-09 · Boxiang Zhang, Zunran Wang, Yonggen Ling, Yuanyuan Guan, Shenghao Zhang, Wenhui Li

Existing methods of cross-modal domain adaptation for 3D semantic segmentation predict results only via 2D-3D complementarity that is obtained by cross-modal feature matching. However, as lacking supervision in the target domain, the complementarity is not always reliable. The results are not ideal when the domain gap is large. To solve the problem of lacking supervision, we introduce masked modeling into this task and propose a method Mx2M, which utilizes masked cross-modality modeling to reduce the large domain gap. Our Mx2M contains two components. One is the core solution, cross-modal removal and prediction (xMRP), which makes the Mx2M adapt to various scenarios and provides cross-modal self-supervision. The other is a new way of cross-modal feature matching, the dynamic cross-modal filter (DxMF) that ensures the whole method dynamically uses more suitable 2D-3D complementarity. Evaluation of the Mx2M on three DA scenarios, including Day/Night, USA/Singapore, and A2D2/SemanticKITTI, brings large improvements over previous methods on many metrics.

📄 PDF Abstract BibTeX arXiv:2307.04231

Code (0)

등록된 구현이 없습니다.

Tasks

3D Semantic SegmentationDomain AdaptationSemantic Segmentation

Similar Papers 제목 키워드 기반

UrFound: Towards Universal Retinal Foundation Models via Knowledge-Guided Masked Modeling

2024-08-10 · Kai Yu, Yang Zhou, Yang Bai, Zhi Da Soh 외

Retinal foundation models aim to learn generalizable representations from diverse retinal images, facilitating label-efficient model adaptation across various ophthalmic tasks. Despite their success, current retinal foun…

Representation Learning

Test-Time Adaptation for Visual Document Understanding

2022-06-15 · Sayna Ebrahimi, Sercan O. Arik, Tomas Pfister

For visual document understanding (VDU), self-supervised pretraining has been shown to successfully generate transferable representations, yet, effective adaptation of such representations to distribution shifts at test-…

document understandingDomain AdaptationLanguage ModelingLanguage Modelling+6

Masked Vision and Language Modeling for Multi-modal Representation Learning

2022-08-03 · Gukyeong Kwon, Zhaowei Cai, Avinash Ravichandran, Erhan Bas 외

In this paper, we study how to use masked signal modeling in vision and language (V+L) representation learning. Instead of developing masked language modeling (MLM) and masked image modeling (MIM) independently, we propo…

cross-modal alignmentLanguage ModelingLanguage ModellingMasked Language Modeling+1

MOSAIC: Masked Objective with Selective Adaptation for In-domain Contrastive Learning

2025-10-19 · Vera Pavlova, Mohammed Makhlouf arxiv

We introduce MOSAIC (Masked Objective with Selective Adaptation for In-domain Contrastive learning), a multi-stage framework for domain adaptation of text embedding models that incorporates joint domain-specific masked s…

Contrastive LearningDomain Adaptation

MLIM: Vision-and-Language Model Pre-training with Masked Language and Image Modeling

2021-09-24 · Tarik Arici, Mehmet Saygin Seyfioglu, Tal Neiman, Yi Xu 외

Vision-and-Language Pre-training (VLP) improves model performance for downstream tasks that require image and text inputs. Current VLP approaches differ on (i) model architecture (especially image embedders), (ii) loss f…

Image ReconstructionLanguage ModelingLanguage ModellingMasked Language Modeling