GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding
Self-supervised 3D representation learning aims to learn effective representations from large-scale unlabeled point clouds. Most existing approaches adopt point discrimination as the pretext task, which assigns matched points in two distinct views as positive pairs and unmatched points as negative pairs. However, this approach often results in semantically identical points having dissimilar representations, leading to a high number of false negatives and introducing a "semantic conflict" problem. To address this issue, we propose GroupContrast, a novel approach that combines segment grouping and semantic-aware contrastive learning. Segment grouping partitions points into semantically meaningful regions, which enhances semantic coherence and provides semantic guidance for the subsequent contrastive representation learning. Semantic-aware contrastive learning augments the semantic information extracted from segment grouping and helps to alleviate the issue of "semantic conflict". We conducted extensive experiments on multiple 3D scene understanding tasks. The results demonstrate that GroupContrast learns semantically meaningful representations and achieves promising transfer learning performance.
Code (1)
Tasks
Contrastive LearningRepresentation LearningScene UnderstandingTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation
Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels. Self-supervised representations encode useful semantic information about images, and as a result, they have already been used…
Instance SegmentationSegmentationSelf-Supervised LearningSemantic Segmentation+3Semantic-Aware Auto-Encoders for Self-Supervised Representation Learning
The resurgence of unsupervised learning can be attributed to the remarkable progress of self-supervised learning, which includes generative (G) and discriminative (D) models. In computer vision, the mainstream self-s…
Image ReconstructionRepresentation LearningSelf-Supervised LearningDistilling Word Meaning in Context from Pre-trained Language Models
In this study, we propose a self-supervised learning method that distils representations of word meaning in context from a pre-trained masked language model. Word representations are the basis for context-aware lexical s…
Language ModelingLanguage ModellingSelf-Supervised LearningSemantic Textual Similarity+2Semantic-Aware Fine-Grained Correspondence
Establishing visual correspondence across images is a challenging and essential task. Recently, an influx of self-supervised methods have been proposed to better learn representations for visual correspondence. However, …
Pose TrackingSelf-Supervised LearningSemantic correspondenceSemantic Segmentation+2Semantic-Aware Generation for Self-Supervised Visual Representation Learning
In this paper, we propose a self-supervised visual representation learning approach which involves both generative and discriminative proxies, where we focus on the former part by requiring the target network to recover …
Representation LearningSemantic Segmentation