# Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition

arXiv: https://arxiv.org/abs/1906.01592 · HTML: https://mlsanity.com/paper/1906.01592/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2019.

## Built on by (most cited first, 25 of 25)

- [PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning](https://mlsanity.com/paper/2211.11682/) (2022)
- [Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation](https://mlsanity.com/paper/2204.07548/) (2022)
- [MVT: Multi-view Vision Transformer for 3D Object Recognition](https://mlsanity.com/paper/2110.13083/) (2021)
- [Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook](https://mlsanity.com/paper/2311.02608/) (2023)
- [Surrogate Modeling of Car Drag Coefficient with Depth and Normal Renderings](https://mlsanity.com/paper/2306.06110/) (2023)
- [Learning Canonical View Representation for 3D Shape Recognition with Arbitrary Views](https://mlsanity.com/paper/2108.07084/) (2021)
- [What's the Situation with Intelligent Mesh Generation: A Survey and Perspectives](https://mlsanity.com/paper/2211.06009/) (2022)
- [Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Views](https://mlsanity.com/paper/2108.03743/) (2021)
- [Noise Injection-based Regularization for Point Cloud Processing](https://mlsanity.com/paper/2103.15027/) (2021)
- [Learning to Select Camera Views: Efficient Multiview Understanding at Few Glances](https://mlsanity.com/paper/2303.06145/) (2023)
- [R2-MLP: Round-Roll MLP for Multi-View 3D Object Recognition](https://mlsanity.com/paper/2211.11085/) (2022)
- [Topology Estimation of Simulated 4D Image Data by Combining Downscaling and Convolutional Neural Networks](https://mlsanity.com/paper/2306.14442/) (2023)
- [Current Symmetry Group Equivariant Convolution Frameworks for Representation Learning](https://mlsanity.com/paper/2409.07327/) (2024)
- [VSFormer: Mining Correlations in Flexible View Set for Multi-view 3D Shape Understanding](https://mlsanity.com/paper/2409.09254/) (2024)
- [Multi-View Active Fine-Grained Recognition](https://mlsanity.com/paper/2206.01153/) (2022)
- [ViewFormer: View Set Attention for Multi-view 3D Shape Understanding](https://mlsanity.com/paper/2305.00161/) (2023)
- [In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender Systems](https://mlsanity.com/paper/2309.01335/) (2023)
- [Self-supervised Graph Neural Network for Mechanical CAD Retrieval](https://mlsanity.com/paper/2406.08863/) (2024)
- [MeshCNN Fundamentals: Geometric Learning through a Reconstructable Representation](https://mlsanity.com/paper/2105.13277/) (2021)
- [Learn to Learn Metric Space for Few-Shot Segmentation of 3D Shapes](https://mlsanity.com/paper/2107.02972/) (2021)
- [Shrinking unit: a Graph Convolution-Based Unit for CNN-like 3D Point Cloud Feature Extractors](https://mlsanity.com/paper/2209.12770/) (2022)
- [Multi-view Structural Convolution Network for Domain-Invariant Point Cloud Recognition of Autonomous Vehicles](https://mlsanity.com/paper/2501.16289/) (2025)
- [LM-MCVT: A Lightweight Multi-modal Multi-view Convolutional-Vision Transformer Approach for 3D Object Recognition](https://mlsanity.com/paper/2504.19256/) (2025)
- [Isolated Bangla Handwritten Character Classification using Transfer Learning](https://mlsanity.com/paper/2509.03061/) (2025)
- [MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshes](https://mlsanity.com/paper/2606.31533/) (2026)

## Abstract (arXiv)

View based strategies for 3D object recognition have proven to be very successful. The state-of-the-art methods now achieve over 90% correct category level recognition performance on appearance images. We improve upon these methods by introducing a view clustering and pooling layer based on dominant sets. The key idea is to pool information from views which are similar and thus belong to the same cluster. The pooled feature vectors are then fed as inputs to the same layer, in a recurrent fashion. This recurrent clustering and pooling module, when inserted in an off-the-shelf pretrained CNN, boosts performance for multi-view 3D object recognition, achieving a new state of the art test set recognition accuracy of 93.8% on the ModelNet 40 database. We also explore a fast approximate learning strategy for our cluster-pooling CNN, which, while sacrificing end-to-end learning, greatly improves its training efficiency with only a slight reduction of recognition accuracy to 93.3%. Our implementation is available at https://github.com/fate3439/dscnn.