Weakly Supervised Discovery of Semantic Attributes
Abstract
We consider the problem of extracting semantic attributes, using only classification labels for supervision. For example, when learning to classify images of birds into species, we would like to observe the emergence of features used by zoologists to classify birds. To tackle this problem, we propose training a neural network with discrete features in the last layer, followed by two heads: a multi-layered perceptron (MLP) and a decision tree. The decision tree utilizes simple binary decision stumps, thus encouraging features to have semantic meaning. We present theoretical analysis, as well as a practical method for learning in the intersection of two hypothesis classes. Compared with various benchmarks, our results show an improved ability to extract a set of features highly correlated with a ground truth set of unseen attributes.
Cite
Text
Ali et al. "Weakly Supervised Discovery of Semantic Attributes." Proceedings of the First Conference on Causal Learning and Reasoning, 2022.Markdown
[Ali et al. "Weakly Supervised Discovery of Semantic Attributes." Proceedings of the First Conference on Causal Learning and Reasoning, 2022.](https://mlanthology.org/clear/2022/ali2022clear-weakly/)BibTeX
@inproceedings{ali2022clear-weakly,
title = {{Weakly Supervised Discovery of Semantic Attributes}},
author = {Ali, Ameen Ali and Galanti, Tomer and Zheltonozhskii, Evgenii and Baskin, Chaim and Wolf, Lior},
booktitle = {Proceedings of the First Conference on Causal Learning and Reasoning},
year = {2022},
pages = {44-69},
volume = {177},
url = {https://mlanthology.org/clear/2022/ali2022clear-weakly/}
}