Abstract
In this paper, we provide a new neural-network based perspective on multi-task learning (MTL) and multi-domain learning (MDL). By introducing the concept of a semantic descriptor, this framework unifies MDL and MTL as well as encompassing various classic and recent MTL/MDL algorithms by interpreting them as different ways of constructing semantic descriptors. Our interpretation
provides an alternative pipeline for zero-shot learning (ZSL), where a model for a novel class can be constructed without training data. Moreover, it leads to a new and practically relevant problem setting of zero-shot domain adaptation (ZSDA), which is the analogous to ZSL but for novel domains: A model for an unseen domain can be generated by its semantic descriptor. Experiments across this range of problems demonstrate that our framework outperforms a variety of alternatives.
provides an alternative pipeline for zero-shot learning (ZSL), where a model for a novel class can be constructed without training data. Moreover, it leads to a new and practically relevant problem setting of zero-shot domain adaptation (ZSDA), which is the analogous to ZSL but for novel domains: A model for an unseen domain can be generated by its semantic descriptor. Experiments across this range of problems demonstrate that our framework outperforms a variety of alternatives.
| Original language | English |
|---|---|
| Title of host publication | 3rd International Conference on Learning Representations (ICLR) |
| Number of pages | 9 |
| Publication status | Published - 2015 |
| Event | 3rd International Conference on Learning Representations - The Hilton San Diego Resort & Spa, San Diego, United States Duration: 7 May 2015 → 9 May 2015 https://iclr.cc/archive/www/doku.php%3Fid=iclr2015:main.html |
Conference
| Conference | 3rd International Conference on Learning Representations |
|---|---|
| Abbreviated title | ICLR 2015 |
| Country/Territory | United States |
| City | San Diego |
| Period | 7/05/15 → 9/05/15 |
| Internet address |