CVPR2018

Institute: CUHK, Syney URL: https://arxiv.org/pdf/1805.04409.pdf Author: http://danxu-research.weebly.com/ (CVPR2018 4편인 저자, 포텟터진듯) Keyword: DepthEstimation, SceneParsing Interest: 2

성능이드라마특하게오른것은 아님듯 #기존 Multi-task Learning의 단점을 극복해보고자노력함

In this paper we tackle the problem of simultaneous depth estimation and scene parsing in a joint CNN. The task can be typically treated as a deep multi-task learning problem.
Different from previous methods directly optimizing multiple tasks given the input training data, this paper proposes a novel multi-task guided prediction-and-distillation network (PAD-Net), which first predicts a set of intermediate auxiliary tasks ranging from low level to high level, and then the predictions from these intermediate auxiliary tasks are utilized as multi-modal input via our proposed multi-modal distillation modules for the final tasks.