Teaching Categories to Human Learners with Visual Explanations
This addresses the problem of improving learning efficiency for human students in categorization tasks, though it is incremental as it builds on existing teaching frameworks.
The paper tackles the problem of computer-assisted teaching by providing interpretable visual explanations instead of just labels, and shows that human learners achieve better test set performance on challenging categorization tasks with this approach compared to existing methods.
We study the problem of computer-assisted teaching with explanations. Conventional approaches for machine teaching typically only provide feedback at the instance level e.g., the category or label of the instance. However, it is intuitive that clear explanations from a knowledgeable teacher can significantly improve a student's ability to learn a new concept. To address these existing limitations, we propose a teaching framework that provides interpretable explanations as feedback and models how the learner incorporates this additional information. In the case of images, we show that we can automatically generate explanations that highlight the parts of the image that are responsible for the class label. Experiments on human learners illustrate that, on average, participants achieve better test set performance on challenging categorization tasks when taught with our interpretable approach compared to existing methods.