Disjoint Label Space Transfer Learning with Common Factorised Space
It addresses a challenging problem in transfer learning for domains with non-overlapping labels, though it appears incremental as it builds on existing methods.
The paper tackles transfer learning with disjoint label spaces between source and target domains, proposing a unified model that outperforms alternatives in unsupervised and semi-supervised settings.
In this paper, a unified approach is presented to transfer learning that addresses several source and target domain label-space and annotation assumptions with a single model. It is particularly effective in handling a challenging case, where source and target label-spaces are disjoint, and outperforms alternatives in both unsupervised and semi-supervised settings. The key ingredient is a common representation termed Common Factorised Space. It is shared between source and target domains, and trained with an unsupervised factorisation loss and a graph-based loss. With a wide range of experiments, we demonstrate the flexibility, relevance and efficacy of our method, both in the challenging cases with disjoint label spaces, and in the more conventional cases such as unsupervised domain adaptation, where the source and target domains share the same label-sets.