arXiv (Cornell University) · 2018 · 486 citations · 13 references
ComputingComputer ScienceLiteratureComputational LinguisticsMachine LearningNatural Language ProcessingDeep LearningNeural NetworksRepresentation LearningBenchmark Datasets
Machine learning research often prioritizes benchmark performance, yet there is a growing call to align tasks with socially or culturally relevant problems. The authors introduce Kuzushiji-MNIST, Kuzushiji-49, and Kuzushiji-Kanji to encourage the ML community to explore classical Japanese literature. They provide three datasets—Kuzushiji-MNIST, Kuzushiji-49, and Kuzushiji-Kanji—comprising handwritten cursive Japanese characters for machine learning tasks. The datasets are available at https://github.com/rois-codh/kmnist.
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
13
Auto-Encoding Variational Bayes
Diederik P. Kingma, Max Welling · UvA-DARE (University of Amsterdam) · 2013 · 15.6K citations · Full text
mixup: Beyond Empirical Risk Minimization
Hongyi Zhang, Moustapha Cissé, Yann Dauphin et al. · arXiv (Cornell University) · 2017 · 4.8K citations · Full text
Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
Konstantinos Bousmalis, Nathan Silberman, David Dohan et al. · 2017 · 1.6K citations