Zero-Shot Task Transfer

Arghya Pal () and Vineeth N. Balasubramanian ()
Additional contact information
Arghya Pal: Indian Institute of Technology
Vineeth N. Balasubramanian: Indian Institute of Technology

Chapter Chapter 13 in Domain Adaptation in Computer Vision with Deep Learning, 2020, pp 235-256 from Springer

Abstract: Abstract Cognitive science has shown results on how human subjects (human children) and other mammals adapt to an entirely novel task (depth measurement) by understanding the association with already learned tasks (self-motion, shoulder movements) without receiving an explicit supervision. Motivated by such prior work, in this chapter, we present a meta-regression algorithm that regresses model parameters of zero-shot tasks from the model parameters of known tasks and the correlation of known and zero-shot tasks. The proposed method is evaluated on the Taskonomy dataset [54] considering surface normal estimation, depth estimation, room layout and camera pose estimation as zero-shot tasks. Our proposed methodology outperforms state-of-the-art models (which use ground truth) on each of our zero-shot tasks, showing promise on zero-shot task transfer. We also conducted extensive experiments to study the various choices of our methodology, as well as showed how the proposed method can also be used in transfer learning. To the best of our knowledge, this is the first such effort on zero-shot learning in the task space.

Keywords: Transfer learning; Zero-shot task learning; Crowd sourcing; Dawid-Skene (search for similar items in EconPapers)
Date: 2020
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-030-45529-3_13

Ordering information: This item can be ordered from
http://www.springer.com/9783030455293

DOI: 10.1007/978-3-030-45529-3_13

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().