Improving Multiple Machine Vision Tasks in the Compressed Domain

Jinming Liu, Heming Sun*, Jiro Katto

*この研究の対応する著者

研究成果: Conference contribution

3 被引用数 (Scopus)

抄録

There is a growing number of images that are analyzed by machines rather than just humans. Recently, most machine vision tasks are based on decoded images which require an image compression (encoding/decoding) framework. However, using the decoded images in the pixel-domain has two drawbacks: 1) the complexity is high for the decoder part, 2) the accuracy (e.g., mIoU, mean absolute error, and average precision) of machine vision tasks will be degraded since decoded images only aim to optimize the human perceived quality (e.g., PSNR) so that information required for machine vision tasks will be lost during the decoding process. In this paper, we improve the machine vision tasks in the compressed domain. 1) A gate module is utilized to effectively select some compressed-domain features. 2) Knowledge distillation is introduced to improve the accuracy. 3) A training strategy is explored to support multiple tasks including the image compression. The experimental results show that we can achieve better rate-accuracy/distortion and lower complexity compared with the state-of-the-art pixel-domain work that can take both machine and human vision tasks.

本文言語English
ホスト出版物のタイトル2022 26th International Conference on Pattern Recognition, ICPR 2022
出版社Institute of Electrical and Electronics Engineers Inc.
ページ331-337
ページ数7
ISBN(電子版)9781665490627
DOI
出版ステータスPublished - 2022
イベント26th International Conference on Pattern Recognition, ICPR 2022 - Montreal, Canada
継続期間: 2022 8月 212022 8月 25

出版物シリーズ

名前Proceedings - International Conference on Pattern Recognition
2022-August
ISSN(印刷版)1051-4651

Conference

Conference26th International Conference on Pattern Recognition, ICPR 2022
国/地域Canada
CityMontreal
Period22/8/2122/8/25

ASJC Scopus subject areas

  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Improving Multiple Machine Vision Tasks in the Compressed Domain」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