Weakly Supervised Discovery of Semantic Attributes

Ameen Ali, Tomer Galanti, Evgenii Zheltonozhskii, Chaim Baskin, Lior Wolf

Research output: Contribution to journalConference articlepeer-review


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.

Original languageEnglish
Pages (from-to)44-69
Number of pages26
JournalProceedings of Machine Learning Research
StatePublished - 2022
Event1st Conference on Causal Learning and Reasoning, CLeaR 2022 - Eureka, United States
Duration: 11 Apr 202213 Apr 2022


FundersFunder number
European Research Council
Horizon 2020ERC CoG 725974


    • Feature discovery
    • explainability
    • quantization


    Dive into the research topics of 'Weakly Supervised Discovery of Semantic Attributes'. Together they form a unique fingerprint.

    Cite this