mlsanityData to 7 Oct 2026

3D Compositional Zero-shot Learning with DeCompositional Consensus

arXiv 2111.14673 ↗First posted 29 Nov 2021cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Parts represent a basic unit of geometric and semantic similarity across different objects. We argue that part knowledge should be composable beyond the observed object classes. Towards this, we present 3D Compositional Zero-shot Learning as a problem of part generalization from seen to unseen object classes for semantic segmentation. We provide a structured study through benchmarking the task with the proposed Compositional-PartNet dataset. This dataset is created by processing the original PartNet to maximize part overlap across different objects. The existing point cloud part segmentation methods fail to generalize to unseen object classes in this setting. As a solution, we propose DeCompositional Consensus, which combines a part segmentation network with a part scoring network. The key intuition to our approach is that a segmentation mask over some parts should have a consensus with its part scores when each part is taken apart. The two networks reason over different part combinations defined in a per-object part prior to generate the most suitable segmentation mask. We demonstrate that our method allows compositional zero-shot segmentation and generalized zero-shot classification, and establishes the state of the art on both tasks.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 41 of its 65 references that are in the map. First posted on arXiv 29 Nov 2021.

Builds on

41 of 65 references.

References · 41

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  5. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  7. 2017Dynamic Routing Between Capsulescited by 689
  8. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  9. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  10. 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
  11. 2018Videos as Space-Time Region Graphscited by 221
  12. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
29 more
  1. 2019RIO: 3D Object Instance Re-Localization in Changing Indoor Environmentscited by 187
  2. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  3. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  4. 2019CvxNet: Learnable Convex Decompositioncited by 173
  5. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 123
  6. 2019Task-Driven Modular Networks for Zero-Shot Compositional Learningcited by 121
  7. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  8. 20183D Point Capsule Networkscited by 106
  9. 2021Open World Compositional Zero-Shot Learningcited by 100
  10. 20213D AffordanceNet: A Benchmark for Visual Object Affordance Understandingcited by 100
  11. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
  12. 2020Symmetry and Group in Attribute-Object Compositionscited by 89
  13. 2020A causal view of compositional zero-shot recognitioncited by 78
  14. 2019Putting Humans in a Scene: Learning Affordance in 3D Indoor Environmentscited by 72
  15. 2020Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Imagecited by 72
  16. 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
  17. 2019ConvPoint: Continuous Convolutions for Point Cloud Processingcited by 62
  18. 2021Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Cloudscited by 55
  19. 2021Learning Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 49
  20. 2019Transductive Zero-Shot Learning for 3D Point Cloud Classificationcited by 39
  21. 2019Zero-shot Learning of 3D Point Cloud Objectscited by 34
  22. 2020Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categoriescited by 29
  23. 2020Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patchescited by 27
  24. 2019Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objectscited by 24
  25. 2016Do semantic parts emerge in Convolutional Neural Networks?cited by 23
  26. 2018Attributes as Operators: Factorizing Unseen Attribute-Object Compositionscited by 20
  27. 2020Learning to Move with Affordance Mapscited by 15
  28. 2021Learning Fine-Grained Segmentation of 3D Shapes without Part Labelscited by 14
  29. 2021Unsupervised Pose-Aware Part Decomposition for 3D Articulated Objectscited by 12

Built on by

Cited by year

Citing papers per year: 2022: 8; 2023: 4; 2024: 3; 2025: 1.

16 papers.

Sort:

  1. 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 186
  2. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 117
  3. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  4. 2022I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classificationcited by 54
  5. 2023Zero-Shot 3D Shape Correspondencecited by 33
  6. 2022I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classificationcited by 27
  7. 2022PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categoriescited by 21
  8. 2024Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learningcited by 20
  9. 2023Iterative Superquadric Recomposition of 3D Objects from Multiple Viewscited by 13
  10. 2024HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generationcited by 8
  11. 2024On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Surveycited by 5
  12. 2025OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fieldscited by 5
4 more
  1. 2022SupeRGB-D: Zero-shot Instance Segmentation in Cluttered Indoor Environmentscited by 4
  2. 2023Open-Pose 3D Zero-Shot Learning: Benchmark and Challengescited by 4
  3. 2022PartCom: Part Composition Learning for 3D Open-Set Recognitioncited by 1
  4. 2022Simple Primitives with Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-shot Learningcited by 0