Learning to Learn in a Semi-Supervised Fashion
This addresses semi-supervised learning challenges in tasks like person re-identification or image retrieval, offering a novel approach that improves performance, though it appears incremental in its method adaptation.
The paper tackles semi-supervised learning with disjoint label sets between labeled and unlabeled data, proposing a meta-learning scheme that transfers semantics-oriented similarity representations from labeled to unlabeled data, achieving superior performance over state-of-the-art methods in experiments.
To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like in person re-identification or image retrieval. Our learning scheme exploits the idea of leveraging information from labeled to unlabeled data. Instead of fitting the associated class-wise similarity scores as most meta-learning algorithms do, we propose to derive semantics-oriented similarity representations from labeled data, and transfer such representation to unlabeled ones. Thus, our strategy can be viewed as a self-supervised learning scheme, which can be applied to fully supervised learning tasks for improved performance. Our experiments on various tasks and settings confirm the effectiveness of our proposed approach and its superiority over the state-of-the-art methods.