LAGO: Probabilitis AND-OR Attribute Grouping for Zero-Shot Learning

Uncertainty in Artificial Intelligence (UAI), 2018

Yuval Atzmon and Gal Chechik


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 and ESZSL. Interestingly, taking only one singleton group for each attribute, introduces a new soft-relaxation of DAP, that outperforms DAP by ~40%.

Cite our paper

title={Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning},
author={Atzmon, Yuval and Chechik, Gal},
booktitle={Proceedings of the Thirty-Forth Conference on Uncertainty in Artificial Intelligence},

Short Video