<ul><li>Researchers propose an interpretable model for few-shot learning based on human-friendly attributes.</li><li>The model utilizes an online attribute selection mechanism to filter out irrelevant attributes in each episode.</li><li>An automated mechanism is introduced to detect episodes with insufficient available attributes and augment them with learned unknown attributes.</li><li>The proposed method achieves results comparable to black-box few-shot learning models and outperforms other methods in terms of decision alignment with human understanding.</li></ul>

Interpretable Few-shot Learning with Online Attribute Selection

Discover more