Novel Class Discovery for 3D Point Cloud Semantic Segmentation
Luigi Riz, Cristiano Saltori, Elisa Ricci, Fabio Poiesi
2023Year
8Top-tier citations
Abstract
Novel Class Discovery road vegetation base classes vehicle novel classes rider vegetation road rider vehicle vehicle predictions vegetation road supervision unlabelled ? unlabelled ? unlabelled ? Novel Class Discovery vehicle novel classes rider road vegetation base classes Figure 1. Novel Class Discovery for 3D point cloud semantic segmentation seeks to recognise novel classes by clustering unlabelled novel points with similar semantic features and by exploiting only the knowledge of a set of labelled samples corresponding to the base classes.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers8
- Towards Label-free Scene Understanding by Vision Foundation ModelsRunnan Chen, Youquan Liu, Lingdong Kong, Nenglun Chen et al.NeurIPS 2023 · 82 citations
- Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category DiscoverySarah Rastegar, Hazel Doughty, Cees SnoekNeurIPS 2023 · 55 citations
- Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and ReasoningYang Li, Aming Wu, Zihao Zhang, Yahong HanNeurIPS 2025 · 2 citations
- Generalized Class Discovery in Instance SegmentationCuong Manh Hoang, Yeejin Lee, Byeongkeun KangAAAI 2025 · 2 citations
- Building a Strong Pre-Training Baseline for Universal 3D Large-Scale PerceptionHaoming Chen, Zhizhong Zhang, Yanyun Qu, Ruixin Zhang et al.CVPR 2024
Builds on19
- Unsupervised Learning of Visual Features by Contrasting Cluster AssignmentsMathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal et al.NeurIPS 2020 · 5,249 citations
- KPConv: Flexible and Deformable Convolution for Point CloudsHugues Thomas, Charles R. Qi, Jean-Emmanuel Deschaud, Beatriz Marcotegui et al.ICCV 2019 · 3,193 citations
- SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR SequencesJens Behley, Martin Garbade, Andres Milioto, Jan Quenzel et al.ICCV 2019 · 2,345 citations
- Invariant Information Clustering for Unsupervised Image Classification and SegmentationXu Ji, Andrea Vedaldi, João F. HenriquesICCV 2019 · 956 citations
- Self-labelling via simultaneous clustering and representation learningYuki Markus Asano, Christian Rupprecht, Andrea VedaldiICLR 2020 · 873 citations
Related papers
- Geometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud SegmentationZihao Zhang, Aming Wu, Li Yang, Yahong Han et al.CVPR 2026
- Learning to Discover and Detect ObjectsVladimir Fomenko, Ismail Elezi, Deva Ramanan, Laura Leal-Taixé et al.NeurIPS 2022 · 14 citations
- Meta Discovery: Learning to Discover Novel Classes given Very Limited DataHaoang Chi, Feng Liu, Wenjing Yang, Long Lan et al.ICLR 2022 · 52 citations
- Semantic-Guided Novel Category DiscoveryWeishuai Wang, Ting Lei, Qingchao Chen, Yang LiuAAAI 2024 · 3 citations
- Novel Class Discovery in Semantic SegmentationYuyang Zhao, Zhun Zhong, Nicu Sebe, Gim Hee LeeCVPR 2022 · 27 citations
