Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth. (arXiv:2206.10562v2 [cs.CV] UPDATED)

Multi-task learning (MTL) paradigm focuses on jointly learning two or more
tasks, aiming for significant improvement w.r.t model's generalizability,
performance, and training/inference memory footprint. The aforementioned
benefits become ever so indispensable in the case of joint training for
vision-related {\bf dense} prediction tasks. In this work, we tackle the MTL
problem of two dense tasks, i.e., semantic segmentation and depth estimation,
and present a novel attention module called Cross-Channel Attention Module
({CCAM}), which facilitates effective feature sharing along each channel …

arxiv semantics semi-supervised semi-supervised learning supervised learning