# Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning

arXiv: https://arxiv.org/abs/1806.02664 · HTML: https://mlsanity.com/paper/1806.02664/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2018.

## Built on by (most cited first, 6 of 6)

- ["This is my unicorn, Fluffy": Personalizing frozen vision-language representations](https://mlsanity.com/paper/2204.01694/) (2022)
- [Multimodal Foundation Models for Zero-shot Animal Species Recognition in Camera Trap Images](https://mlsanity.com/paper/2311.01064/) (2023)
- [Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learning](https://mlsanity.com/paper/2112.00410/) (2021)
- [pRSL: Interpretable Multi-label Stacking by Learning Probabilistic Rules](https://mlsanity.com/paper/2105.13850/) (2021)
- [Text2Model: Text-based Model Induction for Zero-shot Image Classification](https://mlsanity.com/paper/2210.15182/) (2022)
- [Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis](https://mlsanity.com/paper/2111.14182/) (2021)

## Abstract (arXiv)

In zero-shot learning (ZSL), a classifier is trained to recognize visual classes without any image samples. Instead, it is given semantic information about the class, like a textual description or a set of attributes. Learning from attributes could benefit from explicitly modeling structure of the attribute space. Unfortunately, learning of general structure from empirical samples is hard with typical dataset sizes. Here we describe LAGO, a probabilistic model designed to capture natural soft and-or relations across groups of attributes. We show how this model can be learned end-to-end with a deep attribute-detection model. The soft group structure can be learned from data jointly as part of the model, and can also readily incorporate prior knowledge about groups if available. The soft and-or structure succeeds to capture meaningful and predictive structures, improving the accuracy of zero-shot learning on two of three benchmarks. Finally, LAGO reveals a unified formulation over two ZSL approaches: DAP (Lampert et al., 2009) and ESZSL (Romera-Paredes & Torr, 2015). Interestingly, taking only one singleton group for each attribute, introduces a new soft-relaxation of DAP, that outperforms DAP by ~40.