The human ability to synchronize the feedback from all their senses inspired recent works in multi-task and multi-modal learning. While these works rely on expensive supervision, our multi-task graph requires only pseudo-labels from expert models. Every graph node represents a task, and each edge learns between tasks transformations. Once initialized, the graph learns self-supervised, based on a novel consensus shift algorithm that intelligently exploits the agreement between graph pathways to generate new pseudo-labels for the next learning cycle. We demonstrate significant improvement from one unsupervised learning iteration to the next, outperforming related recent methods in extensive multi-task learning experiments on two challenging datasets. Our code is available at https://github.com/bit-ml/cshift.
@article{arxiv.2103.14417,
title = {Self-Supervised Learning in Multi-Task Graphs through Iterative Consensus Shift},
author = {Emanuela Haller and Elena Burceanu and Marius Leordeanu},
journal= {arXiv preprint arXiv:2103.14417},
year = {2021}
}
Comments
Accepted at The British Machine Vision Conference (BMVC) 2021, 12 pages, 6 figures, 5 tables