Classification of scaled texture patterns with transfer learning
作者：
Highlights：
• We seek to classify texture when few scale variations are available for training.
• Existing methods use a pure-learning approach with all scales present for training.
• We use transfer learning to learn the map from atypical to typical texture scales.
• Classifiers equipped with learned maps may use few scale variations for training.
• As training scales increase, the gap between transfer and pure learning approaches diminishes.
摘要
•We seek to classify texture when few scale variations are available for training.•Existing methods use a pure-learning approach with all scales present for training.•We use transfer learning to learn the map from atypical to typical texture scales.•Classifiers equipped with learned maps may use few scale variations for training.•As training scales increase, the gap between transfer and pure learning approaches diminishes.
论文关键词：Texture classification,Texture scaling,Transfer learning,Partial least-square regression,Coupled dictionary learning,Local binary patterns
论文评审过程：Received 4 February 2018, Revised 9 November 2018, Accepted 24 November 2018, Available online 29 November 2018, Version of Record 11 December 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.11.033
