English

Learning Across Tasks and Domains

Computer Vision and Pattern Recognition 2019-10-04 v2

Abstract

Recent works have proven that many relevant visual tasks are closely related one to another. Yet, this connection is seldom deployed in practice due to the lack of practical methodologies to transfer learned concepts across different training processes. In this work, we introduce a novel adaptation framework that can operate across both task and domains. Our framework learns to transfer knowledge across tasks in a fully supervised domain (e.g., synthetic data) and use this knowledge on a different domain where we have only partial supervision (e.g., real data). Our proposal is complementary to existing domain adaptation techniques and extends them to cross tasks scenarios providing additional performance gains. We prove the effectiveness of our framework across two challenging tasks (i.e., monocular depth estimation and semantic segmentation) and four different domains (Synthia, Carla, Kitti, and Cityscapes).

Keywords

Cite

@article{arxiv.1904.04744,
  title  = {Learning Across Tasks and Domains},
  author = {Pierluigi Zama Ramirez and Alessio Tonioni and Samuele Salti and Luigi Di Stefano},
  journal= {arXiv preprint arXiv:1904.04744},
  year   = {2019}
}

Comments

Accepted at ICCV 2019

R2 v1 2026-06-23T08:34:23.514Z