Deep Learning for Classical Japanese Literature

Code

• github.com/rois-codh/kmnist
  OfficialIn papernone★ 0
• github.com/huckiyang/MOT-Kuzushiji-Fashion-Video
  pytorch★ 3
• github.com/christianversloot/extra_keras_datasets
  tf★ 0
• github.com/xyntechx/Manga-Layout-Analysis
  none★ 0
• github.com/khaamosh/Deep-Learning-Japanese-Character-Recognition
  pytorch★ 0
• github.com/oleg-kufirin/recognizing-handwritten-hiragana-symbols
  pytorch★ 0
• github.com/mv-lab/kuzushiji-recognition
  pytorch★ 0
• github.com/elisiojsj/Kuzushiji-49
  pytorch★ 0
• github.com/hardmaru/kanji2kanji
  tf★ 0
• github.com/christianversloot/keras-cnn
  none★ 0

Abstract

Much of machine learning research focuses on producing models which perform well on benchmark tasks, in turn improving our understanding of the challenges associated with those tasks. From the perspective of ML researchers, the content of the task itself is largely irrelevant, and thus there have increasingly been calls for benchmark tasks to more heavily focus on problems which are of social or cultural relevance. In this work, we introduce Kuzushiji-MNIST, a dataset which focuses on Kuzushiji (cursive Japanese), as well as two larger, more challenging datasets, Kuzushiji-49 and Kuzushiji-Kanji. Through these datasets, we wish to engage the machine learning community into the world of classical Japanese literature. Dataset available at https://github.com/rois-codh/kmnist

Tasks

Benchmark Results

Reproductions