Image selection based on autoencoder neural network and application to the semi-supervised image classification

• SINGH Tushar

  AWL inc.

• GAURAV Ashish Kumar

  AWL inc. IIT Kharagpur

• TSUCHIDA Yasuhiro

  AWL inc.

• GHOURABI Fadoua

  AWL inc.

抄録

Convolutional neural networks (CNNs) are becoming a key technology in processing and analyzing real-time video streams, such as security videos. When pre-processing video streams for training CNNs by splitting into image frames, we generate a large-scale image dataset from which a subset is used for training models. The random selection of a subset ignores the properties of the data and produces a repetitive dataset, which is not useful for training. This paper presents an image selection approach based on the autoencoder neural network. The autoencoder projects high-dimensional image feature vectors into a low-dimension latent space for effective analysis of image similarity. This approach allows not only to select representative images but also to facilitate the pseudo-labeling of unlabeled data. In this paper, through experiments with autoencoder, we show the benefits of this method in selecting images for training. We also explain the application to a semi-supervised image classification problem where our approach significantly enhances the accuracy comparing to random selection.

収録刊行物

• 人工知能学会全国大会論文集

  人工知能学会全国大会論文集 JSAI2020 (0), 2K1ES202-2K1ES202, 2020

  一般社団法人 人工知能学会

キーワード

• data sampling
• semi-supervised deep learning
• image classification
• autoencoder

詳細情報

• CRID: 1390003825189369472
• NII論文ID: 130007856898
• DOI: 10.11517/pjsai.jsai2020.0_2k1es202
• 本文言語コード: ja
• データソース種別:
  • JaLC
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可