Deep convolutional networks do not classify based on global object shape

類似資料

• Local Features and Global Shape Information in Object Classification by Deep Convolutional Neural Networks
  著者:: Baker, Nicholas, 等
  出版事項: (2020)
• Non-rigid illusory contours and global shape transformations defined by spatiotemporal boundary formation
  著者:: Erlikhman, Gennady, 等
  出版事項: (2014)
• Transfer of Learning in the Convolutional Neural Networks on Classifying Geometric Shapes Based on Local or Global Invariants
  著者:: Zheng, Yufeng, 等
  出版事項: (2021)
• From Flashes to Edges to Objects: Recovery of Local Edge Fragments Initiates Spatiotemporal Boundary Formation
  著者:: Erlikhman, Gennady, 等
  出版事項: (2016)
• Transfer Learning with Deep Convolutional Neural Networks for Classifying Cellular Morphological Changes
  著者:: Kensert, Alexander, 等
  出版事項: (2019)