Semantics-driven Attentive Few-shot Learning over Clean and Noisy Samples
This work addresses a fundamental challenge in few-shot learning for machine learning researchers, but it appears incremental as it builds on existing meta-learning approaches.
The paper tackled the problem of ambiguities in few-shot learning due to limited training samples by proposing a semantics-driven model with attention mechanisms, achieving effective performance in both clean and noisy settings.
Over the last couple of years few-shot learning (FSL) has attracted great attention towards minimizing the dependency on labeled training examples. An inherent difficulty in FSL is the handling of ambiguities resulting from having too few training samples per class. To tackle this fundamental challenge in FSL, we aim to train meta-learner models that can leverage prior semantic knowledge about novel classes to guide the classifier synthesis process. In particular, we propose semantically-conditioned feature attention and sample attention mechanisms that estimate the importance of representation dimensions and training instances. We also study the problem of sample noise in FSL, towards the utilization of meta-learners in more realistic and imperfect settings. Our experimental results demonstrate the effectiveness of the proposed semantic FSL model with and without sample noise.