Finding NEM-U: Explaining unsupervised representation learning through neural network generated explanation masks

Presenter: Bjørn Leth Møller, Ph.D. Student at Copenhagen University, DIKU, IMAGE section

Abstract: Unsupervised representation learning has become an important ingredient of today's deep learning systems. However, only a few methods exist that explain a learned vector embedding in the sense of providing information about which parts of an input are the most important for its representation. These methods generate the explanation for a given input after the model has been evaluated and tend to produce either inaccurate explanations or are slow, which limits their practical use. To address these limitations, we introduce the Neural Explanation Masks (NEM) framework, which turns a fixed representation model into a self-explaining system by augmenting it with a masking neural network. This network provides occlusion-based explanations in parallel to computing the representations during inference. We present an instance of this framework, the NEM-U (NEM using U-net structure) architecture, which leverages similarities between segmentation and occlusion-based explanation masks. Our experiments show that NEM-U generates explanations faster and with lower complexity compared to the current state-of-the-art while maintaining high accuracy as measured by locality.

‍

In compliance with GDPR consent requirements, presentations given in a Visual Intelligence context may be recorded with the consent of the speaker. All recordings are edited to remove all faces, names and voices of other participants. Questions and comments by the audience will hence be removed and will not appear in the recording.  With the freely given consent from the speaker, recorded presentation may be posted on the Visual Intelligence YouTube channel.