Current studentsExisting staffContact us
 

ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation

Simple item page
dc.contributor.authorLiu, Y.
dc.contributor.authorChen, Y.
dc.contributor.authorWang, H.
dc.contributor.authorBelagiannis, V.
dc.contributor.authorReid, I.
dc.contributor.authorCarneiro, G.
dc.contributor.conferenceEuropean Conference on Computer Vision (ECCV) (29 Sep 2024 - 4 Oct 2024 : Milan, Italy)
dc.contributor.editorRoth, S.
dc.contributor.editorRussakovsky, O.
dc.contributor.editorSattler, T.
dc.contributor.editorVarol, G.
dc.contributor.editorLeonardis, A.
dc.contributor.editorRicci, E.
dc.date.issued2025
dc.description.abstractThe 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.
dc.description.statementofresponsibilityYuyuan Liu, Yuanhong Chen, Hu Wang, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro
dc.identifier.citationLecture Notes in Artificial Intelligence, 2025 / Roth, S., Russakovsky, O., Sattler, T., Varol, G., Leonardis, A., Ricci, E. (ed./s), vol.15059, pp.81-99
dc.identifier.doi10.1007/978-3-031-73232-4_5
dc.identifier.isbn978-3-031-73231-7
dc.identifier.issn0302-9743
dc.identifier.issn1611-3349
dc.identifier.orcidLiu, Y. [0000-0002-1673-9809]
dc.identifier.orcidChen, Y. [0000-0002-8983-2895]
dc.identifier.orcidReid, I. [0000-0001-7790-6423]
dc.identifier.orcidCarneiro, G. [0000-0002-5571-6220]
dc.identifier.urihttps://hdl.handle.net/2440/144359
dc.language.isoen
dc.publisherSpringer Science and Business Media Deutschland GmbH
dc.relation.granthttp://purl.org/au-research/grants/arc/FT190100525
dc.relation.ispartofseriesLecture Notes in Computer Science
dc.rights© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
dc.source.urihttps://doi.org/10.1007/978-3-031-73232-4_5
dc.subjectlarge training sets; modelling semantic LiDAR segmentation
dc.titleItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Research Outputs