# Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories

Source: [Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories](<https://www.sota2.com/research/paper/68fa6aca1e209131cea2a45c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:33:16.767Z

Authors: Tiange Luo, Kaichun Mo, Zhiao Huang, Jiarui Xu, Siyu Hu, Liwei Wang, Hao Su

Published: 2020-02-16T00:23:43.000Z

## Abstract

We address the problem of discovering 3D parts for objects in unseen categories. Being able to learn the geometry prior of parts and transfer this prior to unseen categories pose fundamental challenges on data-driven shape segmentation approaches. Formulated as a contextual bandit problem, we propose a learning-based agglomerative clustering framework which learns a grouping policy to progressively group small part proposals into bigger ones in a bottom-up fashion. At the core of our approach is to restrict the local context for extracting part-level features, which encourages the generalizability to unseen categories. On the large-scale fine-grained 3D part dataset, PartNet, we demonstrate that our method can transfer knowledge of parts learned from 3 training categories to 21 unseen testing categories without seeing any annotated samples. Quantitative comparisons against four shape segmentation baselines shows that our approach achieve the state-of-the-art performance.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Semantic-based Part Segmentation on PartNet (In-distribution)](<https://www.sota2.com/research/sota/semantic-based-part-segmentation-on-partnet-in-distribution.md>): Semantic-based Part Segmentation; PartNet (In-distribution); Mean Recall: 0.352.

- [Semantic-based Part Segmentation on PartNet (Out-of-distribution)](<https://www.sota2.com/research/sota/semantic-based-part-segmentation-on-partnet-out-of-distribution.md>): Semantic-based Part Segmentation; PartNet (Out-of-distribution); Mean Recall: 32.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2002.06478>)

[PDF](<https://arxiv.org/pdf/2002.06478.pdf>)