Pal, Arghya and Balasubramanian, Vineeth N
(2019)
Zero-Shot Task Transfer.
arXiv.
pp. 1-18.
Full text not available from this repository.
(
Request a copy)
Abstract
In this work, we present a novel meta-learning algorithm
TTNet1
that regresses model parameters for novel tasks for
which no ground truth is available (zero-shot tasks). In
order to adapt to novel zero-shot tasks, our meta-learner
learns from the model parameters of known tasks (with
ground truth) and the correlation of known tasks to zeroshot tasks. Such intuition finds its foothold in cognitive science, where a subject (human baby) can adapt to a novel
concept (depth understanding) by correlating it with old
concepts (hand movement or self-motion), without receiving an explicit supervision. We evaluated our model on the
Taskonomy dataset, with four tasks as zero-shot: surface
normal, room layout, depth and camera pose estimation.
These tasks were chosen based on the data acquisition complexity and the complexity associated with the learning process using a deep network. Our proposed methodology outperforms state-of-the-art models (which use ground truth)
on each of our zero-shot tasks, showing promise on zeroshot 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.
Actions (login required)
 |
View Item |
Altmetric
Altmetric