# Disentangling 3D Prototypical Networks For Few-Shot Concept Learning

arXiv: https://arxiv.org/abs/2011.03367 · HTML: https://mlsanity.com/paper/2011.03367/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2020.

## Built on by (most cited first, 15 of 15)

- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Neural Systematic Binder](https://mlsanity.com/paper/2211.01177/) (2022)
- [Video Autoencoder: self-supervised disentanglement of static 3D structure and motion](https://mlsanity.com/paper/2110.02951/) (2021)
- [Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations](https://mlsanity.com/paper/2112.02290/) (2021)
- [Contributions of Shape, Texture, and Color in Visual Recognition](https://mlsanity.com/paper/2207.09510/) (2022)
- [Disentangled Feature Representation for Few-shot Image Classification](https://mlsanity.com/paper/2109.12548/) (2021)
- [Building Intelligent Agents with Neuro-Symbolic Concepts](https://mlsanity.com/paper/2505.06191/) (2025)
- [Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization](https://mlsanity.com/paper/2211.15059/) (2022)
- [Explicitly Disentangled Representations in Object-Centric Learning](https://mlsanity.com/paper/2401.10148/) (2024)
- [Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?](https://mlsanity.com/paper/2212.10292/) (2022)
- [FAMOUS: High-Fidelity Monocular 3D Human Digitization Using View Synthesis](https://mlsanity.com/paper/2410.09690/) (2024)
- [Training-Free Fine-Grained Semantic Segmentations in Low Data Regimes: A FungiTastic Baseline](https://mlsanity.com/paper/2605.22492/) (2026)
- [Active Transfer Prototypical Network: An Efficient Labeling Algorithm for Time-Series Data](https://mlsanity.com/paper/2209.14199/) (2022)
- [Robot Localization and Mapping Final Report -- Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry](https://mlsanity.com/paper/2309.04147/) (2023)
- [RW-Net: Enhancing Few-Shot Point Cloud Classification with a Wavelet Transform Projection-based Network](https://mlsanity.com/paper/2501.03221/) (2025)

## Abstract (arXiv)

We present neural architectures that disentangle RGB-D images into objects' shapes and styles and a map of the background scene, and explore their applications for few-shot 3D object detection and few-shot concept classification. Our networks incorporate architectural biases that reflect the image formation process, 3D geometry of the world scene, and shape-style interplay. They are trained end-to-end self-supervised by predicting views in static scenes, alongside a small number of 3D object boxes. Objects and scenes are represented in terms of 3D feature grids in the bottleneck of the network. We show that the proposed 3D neural representations are compositional: they can generate novel 3D scene feature maps by mixing object shapes and styles, resizing and adding the resulting object 3D feature maps over background scene feature maps. We show that classifiers for object categories, color, materials, and spatial relationships trained over the disentangled 3D feature sub-spaces generalize better with dramatically fewer examples than the current state-of-the-art, and enable a visual question answering system that uses them as its modules to generalize one-shot to novel objects in the scene.