The talk covers the following paper:

"Self-Supervised Learning in Multi-Task Graphs through Iterative Consensus Shift". Emanuela Haller, Elena Burceanu, Marius Leordeanu
The British Machine Vision Conference (BMVC) 2021
Link: [ Ссылка ]

Abstract:
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.

Speaker: Elena Burceanu ([ Ссылка ])

свернуть