# Zero-Shot Task Transfer

## TL;DR

This paper introduces TTNet, a meta-learning algorithm that enables zero-shot task transfer by leveraging correlations between known and unknown tasks, outperforming existing models on several challenging tasks.

## Contribution

The paper presents the first zero-shot learning approach in the task space using a novel meta-learning algorithm, TTNet, which learns from known tasks to adapt to unseen tasks without ground truth.

## Key findings

- Outperforms state-of-the-art models on zero-shot tasks
- Effective in transfer learning scenarios
- Demonstrates the viability of zero-shot task transfer in practice

## Abstract

In this work, we present a novel meta-learning algorithm, i.e. TTNet, 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 zero-shot 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 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 out-performs 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 firstsuch effort on zero-shot learning in the task space.