ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation
Date
2025
Authors
Liu, Y.
Chen, Y.
Wang, H.
Belagiannis, V.
Reid, I.
Carneiro, G.
Editors
Roth, S.
Russakovsky, O.
Sattler, T.
Varol, G.
Leonardis, A.
Ricci, E.
Russakovsky, O.
Sattler, T.
Varol, G.
Leonardis, A.
Ricci, E.
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Lecture Notes in Artificial Intelligence, 2025 / Roth, S., Russakovsky, O., Sattler, T., Varol, G., Leonardis, A., Ricci, E. (ed./s), vol.15059, pp.81-99
Statement of Responsibility
Yuyuan Liu, Yuanhong Chen, Hu Wang, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro
Conference Name
European Conference on Computer Vision (ECCV) (29 Sep 2024 - 4 Oct 2024 : Milan, Italy)
Abstract
The costly and time-consuming annotation process to produce large training sets for modelling semantic LiDAR segmentation methods has motivated the development of semi-supervised learning (SSL) methods. However, such SSL approaches often concentrate on employing consistency learning only for individual LiDAR representations. This narrow focus results in limited perturbations that generally fail to enable effective consistency learning. Additionally, these SSL approaches employ contrastive learning based on the sampling from a limited set of positive and negative embedding samples. This paper introduces a novel semi-supervised LiDAR semantic segmentation framework called ItTakesTwo (IT2). IT2 is designed to ensure consistent predictions from peer LiDAR representations, thereby improving the perturbation effectiveness in consistency learning. Furthermore, our contrastive learning employs informative samples drawn from a distribution of positive and negative embeddings learned from the entire training set. Results on public benchmarks show that our approach achieves remarkable improvements over the previous state-of-the-art (SOTA) methods in the field.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG