Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation

• URL: http://arxiv.org/abs/2403.10001v1
• Date: Fri, 15 Mar 2024 03:58:17 GMT
• Title: Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
• Authors: Jingyi Xu, Weidong Yang, Lingdong Kong, Youquan Liu, Rui Zhang, Qingyuan Zhou, Ben Fei,
• Abstract summary: We study how to harness the knowledge priors learned by 2D visual foundation models to produce more accurate labels for unlabeled target domains. Our method is evaluated on various autonomous driving datasets and the results demonstrate a significant improvement for 3D segmentation task.
• Score: 17.875516787157018
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unsupervised domain adaptation (UDA) is vital for alleviating the workload of labeling 3D point cloud data and mitigating the absence of labels when facing a newly defined domain. Various methods of utilizing images to enhance the performance of cross-domain 3D segmentation have recently emerged. However, the pseudo labels, which are generated from models trained on the source domain and provide additional supervised signals for the unseen domain, are inadequate when utilized for 3D segmentation due to their inherent noisiness and consequently restrict the accuracy of neural networks. With the advent of 2D visual foundation models (VFMs) and their abundant knowledge prior, we propose a novel pipeline VFMSeg to further enhance the cross-modal unsupervised domain adaptation framework by leveraging these models. In this work, we study how to harness the knowledge priors learned by VFMs to produce more accurate labels for unlabeled target domains and improve overall performance. We first utilize a multi-modal VFM, which is pre-trained on large scale image-text pairs, to provide supervised labels (VFM-PL) for images and point clouds from the target domain. Then, another VFM trained on fine-grained 2D masks is adopted to guide the generation of semantically augmented images and point clouds to enhance the performance of neural networks, which mix the data from source and target domains like view frustums (FrustumMixing). Finally, we merge class-wise prediction across modalities to produce more accurate annotations for unlabeled target domains. Our method is evaluated on various autonomous driving datasets and the results demonstrate a significant improvement for 3D segmentation task.

Related papers

• SiamSeg: Self-Training with Contrastive Learning for Unsupervised Domain Adaptation Semantic Segmentation in Remote Sensing [14.007392647145448]
  UDA enables models to learn from unlabeled target domain data while training on labeled source domain data. We propose integrating contrastive learning into UDA, enhancing the model's capacity to capture semantic information. Our SimSeg method outperforms existing approaches, achieving state-of-the-art results.
  arXiv  Detail & Related papers  (2024-10-17T11:59:39Z)
• FPL+: Filtered Pseudo Label-based Unsupervised Cross-Modality Adaptation for 3D Medical Image Segmentation [14.925162565630185]
  We propose an enhanced Filtered Pseudo Label (FPL+)-based Unsupervised Domain Adaptation (UDA) method for 3D medical image segmentation. It first uses cross-domain data augmentation to translate labeled images in the source domain to a dual-domain training set consisting of a pseudo source-domain set and a pseudo target-domain set. We then combine labeled source-domain images and target-domain images with pseudo labels to train a final segmentor, where image-level weighting based on uncertainty estimation and pixel-level weighting based on dual-domain consensus are proposed to mitigate the adverse effect of noisy pseudo
  arXiv  Detail & Related papers  (2024-04-07T14:21:37Z)
• CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D Object Detection [14.063365469339812]
  LiDAR-based 3D Object Detection methods often do not generalize well to target domains outside the source (or training) data distribution. We introduce a novel unsupervised domain adaptation (UDA) method, called CMDA, which leverages visual semantic cues from an image modality. We also introduce a self-training-based learning strategy, wherein a model is adversarially trained to generate domain-invariant features.
  arXiv  Detail & Related papers  (2024-03-06T14:12:38Z)
• Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation [67.07112533415116]
  We present a novel framework that adapts various foundational models for the 3D point cloud segmentation task. Our approach involves making initial predictions of 2D semantic masks using different large vision models. To generate robust 3D semantic pseudo labels, we introduce a semantic label fusion strategy that effectively combines all the results via voting.
  arXiv  Detail & Related papers  (2023-11-03T15:41:15Z)
• BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation [59.99683295806698]
  Cross-modal Unsupervised Domain Adaptation (UDA) aims to exploit the complementarity of 2D-3D data to overcome the lack of annotation in a new domain. We propose cross-modal learning under bird's-eye view for Domain Generalization (DG) of 3D semantic segmentation, called BEV-DG.
  arXiv  Detail & Related papers  (2023-08-12T11:09:17Z)
• SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud [125.9472454212909]
  We present a novel Semi-Supervised Domain Adaptation method for 3D object detection (SSDA3D) SSDA3D includes an Inter-domain Adaptation stage and an Intra-domain Generalization stage. Experiments show that, with only 10% labeled target data, our SSDA3D can surpass the fully-supervised oracle model with 100% target label.
  arXiv  Detail & Related papers  (2022-12-06T09:32:44Z)
• Geometry-Aware Network for Domain Adaptive Semantic Segmentation [64.00345743710653]
  We propose a novel Geometry-Aware Network for Domain Adaptation (GANDA) to shrink the domain gaps. We exploit 3D topology on the point clouds generated from RGB-D images for coordinate-color disentanglement and pseudo-labels refinement in the target domain. Our model outperforms state-of-the-arts on GTA5->Cityscapes and SYNTHIA->Cityscapes.
  arXiv  Detail & Related papers  (2022-12-02T00:48:44Z)
• QuadFormer: Quadruple Transformer for Unsupervised Domain Adaptation in Power Line Segmentation of Aerial Images [12.840195641761323]
  We propose a novel framework designed for domain adaptive semantic segmentation. The hierarchical quadruple transformer combines cross-attention and self-attention mechanisms to adapt transferable context. We present two datasets - ARPLSyn and ARPLReal - to further advance research in unsupervised domain adaptive powerline segmentation.
  arXiv  Detail & Related papers  (2022-11-29T03:15:27Z)
• Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training [57.25828870799331]
  We propose STMono3D, a new self-teaching framework for unsupervised domain adaptation on Mono3D. We develop a teacher-student paradigm to generate adaptive pseudo labels on the target domain. STMono3D achieves remarkable performance on all evaluated datasets and even surpasses fully supervised results on the KITTI 3D object detection dataset.
  arXiv  Detail & Related papers  (2022-04-25T12:23:07Z)
• ST3D: Self-training for Unsupervised Domain Adaptation on 3D ObjectDetection [78.71826145162092]
  We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds. Our ST3D achieves state-of-the-art performance on all evaluated datasets and even surpasses fully supervised results on KITTI 3D object detection benchmark.
  arXiv  Detail & Related papers  (2021-03-09T10:51:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.