Hard Negative Mining for Metric Learning Based Zero-Shot Classification
This incremental improvement addresses zero-shot classification for domain adaptation tasks.
The paper tackled the problem of zero-shot classification by extending a metric learning approach with hard negative mining schemes, resulting in above state-of-the-art performance on three challenging datasets.
Zero-Shot learning has been shown to be an efficient strategy for domain adaptation. In this context, this paper builds on the recent work of Bucher et al. [1], which proposed an approach to solve Zero-Shot classification problems (ZSC) by introducing a novel metric learning based objective function. This objective function allows to learn an optimal embedding of the attributes jointly with a measure of similarity between images and attributes. This paper extends their approach by proposing several schemes to control the generation of the negative pairs, resulting in a significant improvement of the performance and giving above state-of-the-art results on three challenging ZSC datasets.