Generalized Label-Efficient 3D Scene Parsing via Hierarchical Feature Aligned Pre-Training and Region-Aware Fine-tuning

• URL: http://arxiv.org/abs/2312.00663v1
• Date: Fri, 1 Dec 2023 15:47:04 GMT
• Title: Generalized Label-Efficient 3D Scene Parsing via Hierarchical Feature Aligned Pre-Training and Region-Aware Fine-tuning
• Authors: Kangcheng Liu, Yong-Jin Liu, Kai Tang, Ming Liu, Baoquan Chen
• Abstract summary: This work presents a framework for dealing with 3D scene understanding when the labeled scenes are quite limited. To extract knowledge for novel categories from the pre-trained vision-language models, we propose a hierarchical feature-aligned pre-training and knowledge distillation strategy. Experiments with both indoor and outdoor scenes demonstrated the effectiveness of our approach in both data-efficient learning and open-world few-shot learning.
• Score: 55.517000360348725
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural network models have achieved remarkable progress in 3D scene understanding while trained in the closed-set setting and with full labels. However, the major bottleneck for current 3D recognition approaches is that they do not have the capacity to recognize any unseen novel classes beyond the training categories in diverse kinds of real-world applications. In the meantime, current state-of-the-art 3D scene understanding approaches primarily require high-quality labels to train neural networks, which merely perform well in a fully supervised manner. This work presents a generalized and simple framework for dealing with 3D scene understanding when the labeled scenes are quite limited. To extract knowledge for novel categories from the pre-trained vision-language models, we propose a hierarchical feature-aligned pre-training and knowledge distillation strategy to extract and distill meaningful information from large-scale vision-language models, which helps benefit the open-vocabulary scene understanding tasks. To leverage the boundary information, we propose a novel energy-based loss with boundary awareness benefiting from the region-level boundary predictions. To encourage latent instance discrimination and to guarantee efficiency, we propose the unsupervised region-level semantic contrastive learning scheme for point clouds, using confident predictions of the neural network to discriminate the intermediate feature embeddings at multiple stages. Extensive experiments with both indoor and outdoor scenes demonstrated the effectiveness of our approach in both data-efficient learning and open-world few-shot learning. All codes, models, and data are made publicly available at: https://drive.google.com/drive/folders/1M58V-PtR8DBEwD296zJkNg_m2qq-MTAP?usp=sharing.

Related papers

• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• A Review and A Robust Framework of Data-Efficient 3D Scene Parsing with Traditional/Learned 3D Descriptors [10.497309421830671]
  Existing state-of-the-art 3D point cloud understanding methods merely perform well in a fully supervised manner. This work presents a general and simple framework to tackle point cloud understanding when labels are limited.
  arXiv  Detail & Related papers  (2023-12-03T02:51:54Z)
• A Data-efficient Framework for Robotics Large-scale LiDAR Scene Parsing [10.497309421830671]
  Existing state-of-the-art 3D point clouds understanding methods only perform well in a fully supervised manner. This work presents a general and simple framework to tackle point clouds understanding when labels are limited.
  arXiv  Detail & Related papers  (2023-12-03T02:38:51Z)
• 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)
• RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding [46.253711788685536]
  We introduce a 3D-aware SFusion strategy that fuses 3D vision-language pairs derived from multiple 2D foundation models. We devise a region-aware point-discriminative contrastive learning objective to enable robust and effective 3D learning. Our model outperforms prior 3D open-world scene understanding approaches by an average of 17.2% and 9.1% for semantic and instance segmentation.
  arXiv  Detail & Related papers  (2023-04-03T13:30:04Z)
• Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision [65.19589997822155]
  We introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision. We show that the proposed network can be trained with cheap, or even off-the-shelf bounding box-level annotations and subcloud-level tags.
  arXiv  Detail & Related papers  (2022-01-09T09:07:48Z)
• Point Discriminative Learning for Unsupervised Representation Learning on 3D Point Clouds [54.31515001741987]
  We propose a point discriminative learning method for unsupervised representation learning on 3D point clouds. We achieve this by imposing a novel point discrimination loss on the middle level and global level point features. Our method learns powerful representations and achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-08-04T15:11:48Z)
• Weakly-Supervised Action Localization and Action Recognition using Global-Local Attention of 3D CNN [4.924442315857227]
  3D Convolutional Neural Network (3D CNN) captures spatial and temporal information on 3D data such as video sequences. We propose two approaches to improve the visual explanations and classification in 3D CNN.
  arXiv  Detail & Related papers  (2020-12-17T12:29:16Z)
• PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding [107.02479689909164]
  In this work, we aim at facilitating research on 3D representation learning. We measure the effect of unsupervised pre-training on a large source set of 3D scenes.
  arXiv  Detail & Related papers  (2020-07-21T17:59:22Z)

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.