# Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias

arXiv: https://arxiv.org/abs/2101.07296 · HTML: https://mlsanity.com/paper/2101.07296/

## Key facts

- Cited by 118 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 61 references that are in the map.
- First posted on arXiv 18 Jan 2021.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Geometric deep learning on graphs and manifolds using mixture model CNNs](https://mlsanity.com/paper/1611.08402/) (2016)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?](https://mlsanity.com/paper/2003.11539/) (2020)
- [ABC: A Big CAD Model Dataset For Geometric Deep Learning](https://mlsanity.com/paper/1812.06216/) (2018)
- [Relation Networks for Object Detection](https://mlsanity.com/paper/1711.11575/) (2017)
- [Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions](https://mlsanity.com/paper/1812.03664/) (2018)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Probabilistic Model-Agnostic Meta-Learning](https://mlsanity.com/paper/1806.02817/) (2018)
- [Volumetric and Multi-View CNNs for Object Classification on 3D Data](https://mlsanity.com/paper/1604.03265/) (2016)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning](https://mlsanity.com/paper/1911.04623/) (2019)

## Built on by (most cited first, 30 of 118)

- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation](https://mlsanity.com/paper/2301.07525/) (2023)
- [Native and Compact Structured Latents for 3D Generation](https://mlsanity.com/paper/2512.14692/) (2025)
- [SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling](https://mlsanity.com/paper/2503.21732/) (2025)
- [Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images](https://mlsanity.com/paper/2503.13439/) (2025)
- [A General-Purpose Self-Supervised Model for Computational Pathology](https://mlsanity.com/paper/2308.15474/) (2023)
- [ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding](https://mlsanity.com/paper/2506.01853/) (2025)
- [AToken: A Unified Tokenizer for Vision](https://mlsanity.com/paper/2509.14476/) (2025)
- [Make-A-Shape: a Ten-Million-scale 3D Shape Model](https://mlsanity.com/paper/2401.11067/) (2024)
- [KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models](https://mlsanity.com/paper/2407.17773/) (2024)
- [UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation](https://mlsanity.com/paper/2509.25079/) (2025)
- [FastMesh: Efficient Artistic Mesh Generation via Component Decoupling](https://mlsanity.com/paper/2508.19188/) (2025)
- [WorldGrow: Generating Infinite 3D World](https://mlsanity.com/paper/2510.21682/) (2025)
- [Time to augment self-supervised visual representation learning](https://mlsanity.com/paper/2207.13492/) (2022)
- [Cube: A Roblox View of 3D Intelligence](https://mlsanity.com/paper/2503.15475/) (2025)
- [Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation](https://mlsanity.com/paper/2502.14247/) (2025)
- [Pixal3D: Pixel-Aligned 3D Generation from Images](https://mlsanity.com/paper/2605.10922/) (2026)
- [Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition](https://mlsanity.com/paper/2308.09694/) (2023)
- [Orientation Matters: Making 3D Generative Models Orientation-Aligned](https://mlsanity.com/paper/2506.08640/) (2025)
- [Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation](https://mlsanity.com/paper/2509.12815/) (2025)
- [Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion](https://mlsanity.com/paper/2506.17074/) (2025)
- [QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Models](https://mlsanity.com/paper/2509.21420/) (2025)
- [Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2411.01432/) (2024)
- [3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image](https://mlsanity.com/paper/2604.04406/) (2026)
- [A Closer Look at Few-Shot 3D Point Cloud Classification](https://mlsanity.com/paper/2303.18210/) (2023)
- [Self-supervised visual learning from interactions with objects](https://mlsanity.com/paper/2407.06704/) (2024)
- [Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodings](https://mlsanity.com/paper/2411.08017/) (2024)
- [MeshRipple: Structured Autoregressive Generation of Artist-Meshes](https://mlsanity.com/paper/2512.07514/) (2025)
- [Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation](https://mlsanity.com/paper/2512.10949/) (2025)

## Abstract (arXiv)

It is widely accepted that reasoning about object shape is important for object recognition. However, the most powerful object recognition methods today do not explicitly make use of object shape during learning. In this work, motivated by recent developments in low-shot learning, findings in developmental psychology, and the increased use of synthetic data in computer vision research, we investigate how reasoning about 3D shape can be used to improve low-shot learning methods' generalization performance. We propose a new way to improve existing low-shot learning approaches by learning a discriminative embedding space using 3D object shape, and using this embedding by learning how to map images into it. Our new approach improves the performance of image-only low-shot learning approaches on multiple datasets. We also introduce Toys4K, a 3D object dataset with the largest number of object categories currently available, which supports low-shot learning.