0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 3 years have passed since last update.

論文メモ:Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation

Last updated at Posted at 2021-11-11

論文

論文名
Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation

著者
Xuecheng Nie, Jiashi Feng, and Shuicheng Yan.

学会
ECCV2018

概要

 Human ParsingとPose Estimationを同時に行う、かつ相互に利益を適応させることによってお互いの性能を向上させることができるMutual Learning to Adapt(MuLA)。畳み込みニューラルネットワークで実装された本手法はエンドツーエンドで学習可能であり、複数のデータセットで優れた性能を示す。

Xuecheng Nie, Jiashi Feng, and Shuicheng Yan. Mutual learning to adapt for joint human parsing and pose estimation. In ECCV, pages 519–534, 2018.

Human Parsing:人物のパーツごとにセグメンテーションをするタスク

貢献

  • HumanParsingとPoseEstimationを共同かつエンドツーエンドで学習可能なモデル提案
  • 2つのタスクの利益の相互適応モジュール
  • 複数のデータセットでSOTA


Xuecheng Nie, Jiashi Feng, and Shuicheng Yan. Mutual learning to adapt for joint human parsing and pose estimation. In ECCV, pages 519–534, 2018.

評価

  • LIPデータセットにおいて最先端
  • PASCAL-Person-Partデータセットにおいて最先端


Xuecheng Nie, Jiashi Feng, and Shuicheng Yan. Mutual learning to adapt for joint human parsing and pose estimation. In ECCV, pages 519–534, 2018.

LIP:Look Into Person。人物のパーツラベル19個、キーポイント16個。5万枚の画像。

0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?