Neural Information Processing Systems http://nips.cc/

Inourscenario,weassume24 the label of each support set is also given (eg, images of cat and the semantic label'cat'). We found this a realistic25 assumption. On the contrary, AM3 is model-28 agnostic toanymetric-based FSLmethods, asdescribed inthepaper. As pointed by R1 and R3, the proposed approach can potentially44 be used inmanydifferent cross-modal FSL settings involving visual and semantic information.

Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic feature spaces have different structures by definition.

We thank reviewers for detailed and helpful reviews. Table 1 shows the results. If we understand correctly, R2's main concern is that the word embeddings of We believe that it would hardly happen. The reasons are as follows. Second, we can easily assume a FSL scenario in which we have access to the labels of the test set.