Meta-Learning for Multi-Label Few-Shot Classification
This addresses the problem of multi-label classification with limited data for researchers in few-shot learning, though it is incremental as it extends existing single-label methods.
The paper tackles multi-label few-shot classification by creating a benchmark and extending existing methods to handle multiple labels per sample, introducing a neural label count module that improves performance on three datasets (MS-COCO, iMaterialist, Open MIC).
Even with the luxury of having abundant data, multi-label classification is widely known to be a challenging task to address. This work targets the problem of multi-label meta-learning, where a model learns to predict multiple labels within a query (e.g., an image) by just observing a few supporting examples. In doing so, we first propose a benchmark for Few-Shot Learning (FSL) with multiple labels per sample. Next, we discuss and extend several solutions specifically designed to address the conventional and single-label FSL, to work in the multi-label regime. Lastly, we introduce a neural module to estimate the label count of a given sample by exploiting the relational inference. We will show empirically the benefit of the label count module, the label propagation algorithm, and the extensions of conventional FSL methods on three challenging datasets, namely MS-COCO, iMaterialist, and Open MIC. Overall, our thorough experiments suggest that the proposed label-propagation algorithm in conjunction with the neural label count module (NLC) shall be considered as the method of choice.