Cross-task Attention Mechanism for Dense Multi-Task Learning, WACV'23
Authors: Ivan Lopes (Inria), Tuan-Hung Vu (Valeo.ai), Raoul de Charette (Inria) CVF | arXiv | Github Abstract: Multi-task learning has recently become a promising solution for a comprehensive understanding of complex scenes. Not only being memory-efficient, multi-task models with an appropriate design can favor exchange of complementary signals across tasks. In this work, we jointly address 2D semantic segmentation, and two geometry-related tasks, namely dense depth, surface normal estimation as well as edge estimation showing their benefit on indoor and outdoor datasets....