# Learning Compositional Representations for Few-Shot Recognition

arXiv: https://arxiv.org/abs/1812.09213 · HTML: https://mlsanity.com/paper/1812.09213/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2018.

## Built on by (most cited first, 30 of 50)

- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection](https://mlsanity.com/paper/2103.04612/) (2021)
- [Detecting Human-Object Interaction via Fabricated Compositional Learning](https://mlsanity.com/paper/2103.08214/) (2021)
- [Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language](https://mlsanity.com/paper/2210.00482/) (2022)
- [Generating Representative Samples for Few-Shot Classification](https://mlsanity.com/paper/2205.02918/) (2022)
- [Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?](https://mlsanity.com/paper/2203.17271/) (2022)
- [BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning](https://mlsanity.com/paper/2203.01522/) (2022)
- [Probabilistic Compositional Embeddings for Multimodal Image Retrieval](https://mlsanity.com/paper/2204.05845/) (2022)
- [MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition](https://mlsanity.com/paper/2305.07214/) (2023)
- [Prompting Language-Informed Distribution for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.14428/) (2023)
- [Learning Compositional Representation for 4D Captures with Neural ODE](https://mlsanity.com/paper/2103.08271/) (2021)
- [Use Your Head: Improving Long-Tail Video Recognition](https://mlsanity.com/paper/2304.01143/) (2023)
- [When does compositional structure yield compositional generalization? A kernel theory](https://mlsanity.com/paper/2405.16391/) (2024)
- [Attribute Prototype Network for Any-Shot Learning](https://mlsanity.com/paper/2204.01208/) (2022)
- [Contributions of Shape, Texture, and Color in Visual Recognition](https://mlsanity.com/paper/2207.09510/) (2022)
- [H4D: Human 4D Modeling by Learning Neural Compositional Representation](https://mlsanity.com/paper/2203.01247/) (2022)
- [Simple Semantic-Aided Few-Shot Learning](https://mlsanity.com/paper/2311.18649/) (2023)
- [A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices](https://mlsanity.com/paper/2406.08787/) (2024)
- [Disentangled Feature Representation for Few-shot Image Classification](https://mlsanity.com/paper/2109.12548/) (2021)
- [Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learning](https://mlsanity.com/paper/2104.02281/) (2021)
- [vMFNet: Compositionality Meets Domain-generalised Segmentation](https://mlsanity.com/paper/2206.14538/) (2022)
- [MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learning](https://mlsanity.com/paper/2111.00232/) (2021)
- [Hierarchical Compositional Representations for Few-shot Action Recognition](https://mlsanity.com/paper/2208.09424/) (2022)
- [Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awareness](https://mlsanity.com/paper/2109.14120/) (2021)
- [Learning Single/Multi-Attribute of Object with Symmetry and Group](https://mlsanity.com/paper/2110.04603/) (2021)
- [Prototype Completion for Few-Shot Learning](https://mlsanity.com/paper/2108.05010/) (2021)
- [Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learning](https://mlsanity.com/paper/2109.01295/) (2021)
- [Mitigating the Effect of Incidental Correlations on Part-based Learning](https://mlsanity.com/paper/2310.00377/) (2023)
- [Contextualizing Meta-Learning via Learning to Decompose](https://mlsanity.com/paper/2106.08112/) (2021)
- [Learning Compositional Representation for Few-shot Visual Question Answering](https://mlsanity.com/paper/2102.10575/) (2021)

## Abstract (arXiv)

One of the key limitations of modern deep learning approaches lies in the amount of data required to train them. Humans, by contrast, can learn to recognize novel categories from just a few examples. Instrumental to this rapid learning ability is the compositional structure of concept representations in the human brain --- something that deep learning models are lacking. In this work, we make a step towards bridging this gap between human and machine learning by introducing a simple regularization technique that allows the learned representation to be decomposable into parts. Our method uses category-level attribute annotations to disentangle the feature space of a network into subspaces corresponding to the attributes. These attributes can be either purely visual, like object parts, or more abstract, like openness and symmetry. We demonstrate the value of compositional representations on three datasets: CUB-200-2011, SUN397, and ImageNet, and show that they require fewer examples to learn classifiers for novel categories.