Search Results for author: Hanbit Lee

Found 4 papers, 2 papers with code

Contrastive Learning for Unsupervised Image-to-Image Translation

no code implementations7 May 2021 Hanbit Lee, Jinseok Seol, Sang-goo Lee

Image-to-image translation aims to learn a mapping between different groups of visually distinguishable images.

Contrastive Learning Translation +1

Semantics-Preserving Adversarial Training

no code implementations23 Sep 2020 Wonseok Lee, Hanbit Lee, Sang-goo Lee

Adversarial training is a defense technique that improves adversarial robustness of a deep neural network (DNN) by including adversarial examples in the training data.

Adversarial Robustness

Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation

1 code implementation EMNLP 2020 Kang Min Yoo, Hanbit Lee, Franck Dernoncourt, Trung Bui, Walter Chang, Sang-goo Lee

Recent works have shown that generative data augmentation, where synthetic samples generated from deep generative models complement the training dataset, benefit NLP tasks.

Data Augmentation dialog state tracking +4

Style2Vec: Representation Learning for Fashion Items from Style Sets

1 code implementation14 Aug 2017 Hanbit Lee, Jinseok Seol, Sang-goo Lee

With the rapid growth of online fashion market, demand for effective fashion recommendation systems has never been greater.

Image Classification Recommendation Systems +3

Cannot find the paper you are looking for? You can Submit a new open access paper.