Understanding the effects of pre-training for object detectors via eigenspectrum

Yosuke Shinya, Edgar Simo-Serra, Taiji Suzuki

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

ImageNet pre-training has been regarded as essential for training accurate object detectors for a long time. Recently, it has been shown that object detectors trained from randomly initialized weights can be on par with those fine-tuned from ImageNet pre-trained models. However, the effects of pre-training and the differences caused by pre-training are still not fully understood. In this paper, we analyze the eigenspectrum dynamics of the covariance matrix of each feature map in object detectors. Based on our analysis on ResNet-50, Faster R-CNN with FPN, and Mask R-CNN, we show that object detectors trained from ImageNet pre-trained models and those trained from scratch behave differently from each other even if both object detectors have similar accuracy. Furthermore, we propose a method for automatically determining the widths (the numbers of channels) of object detectors based on the eigenspectrum. We train Faster R-CNN with FPN from randomly initialized weights, and show that our method can reduce ~27% of the parameters of ResNet-50 without increasing Multiply-Accumulate operations and losing accuracy. Our results indicate that we should develop more appropriate methods for transferring knowledge from image classification to object detection (or other tasks).

本文言語English
ホスト出版物のタイトルProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1931-1941
ページ数11
ISBN(電子版)9781728150239
DOI
出版ステータスPublished - 2019 10
イベント17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 - Seoul, Korea, Republic of
継続期間: 2019 10 272019 10 28

出版物シリーズ

名前Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

Conference

Conference17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
国/地域Korea, Republic of
CitySeoul
Period19/10/2719/10/28

ASJC Scopus subject areas

  • コンピュータ サイエンスの応用
  • 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

「Understanding the effects of pre-training for object detectors via eigenspectrum」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