Resolution irrelevant encoding and difficulty balanced loss based network independent supervision for multi-person pose estimation

Haiyang Liu, Dingli Luo, Songlin Du, Takeshi Ikenaga

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

Sustainable efforts are made to improve the accuracy performance in multi-person pose estimation, but the current accuracy is still not enough for real-world applications. Besides, most improvement approaches are designed for special basement networks and ignore the speed performance, which results in limited applicability and low cost-performance. This paper proposes two network independent supervision: Resolution Irrelevant Encoding and Difficulty Balanced Loss. The proposed methods reorganize task representatives, the loss calculation method, and the loss punishment ratio in one-stage pose estimation frameworks to improve the joints' location accuracy with general applicability and high computational efficiency. Resolution Irrelevant Encoding fuses heatmaps and proposed inner block offsets to fix pixel-level joints positions without resolution limitations. To improve network training efficiency, Difficulty Balanced Loss adjusts loss weight in spatial and sequential aspects. On the MS COCO keypoints detection benchmark, the mAP of OpenPose trained with our proposals outperforms the OpenPose baseline over 4.9%.

本文言語English
ホスト出版物のタイトルProceedings - 2020 13th International Conference on Human System Interaction, HSI 2020
出版社IEEE Computer Society
ページ112-117
ページ数6
ISBN(電子版)9781728173924
DOI
出版ステータスPublished - 2020 6
イベント13th International Conference on Human System Interaction, HSI 2020 - Tokyo, Japan
継続期間: 2020 6 62020 6 8

出版物シリーズ

名前International Conference on Human System Interaction, HSI
2020-June
ISSN(印刷版)2158-2246
ISSN(電子版)2158-2254

Conference

Conference13th International Conference on Human System Interaction, HSI 2020
国/地域Japan
CityTokyo
Period20/6/620/6/8

ASJC Scopus subject areas

  • 人間とコンピュータの相互作用
  • ソフトウェア

フィンガープリント

「Resolution irrelevant encoding and difficulty balanced loss based network independent supervision for multi-person pose estimation」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル