42 citations · 46 across the 7 of their papers we have counts for
8 papers
Is Cross-modal Information Retrieval Possible without Training?
Hyunjin Choi, Hyunjae Lee, Seongho Joe +1
Encoded representations from a pretrained deep learning model (e.g., BERT text embeddings, penultimate CNN layer activations of an image) convey a rich set of features beneficial f…
D2CSE: Difference-aware Deep continuous prompts for Contrastive Sentence Embeddings
Hyunjae Lee
This paper describes Difference-aware Deep continuous prompt for Contrastive Sentence Embeddings (D2CSE) that learns sentence embeddings. Compared to state-of-the-art approaches, D…
Bayesian Optimization Meets Self-Distillation
HyunJae Lee, Heon Song, Hyeonsoo Lee +3
Bayesian optimization (BO) has contributed greatly to improving model performance by suggesting promising hyperparameter configurations iteratively based on observations from multi…
Improving Multi-fidelity Optimization with a Recurring Learning Rate for Hyperparameter Tuning
HyunJae Lee, Gihyeon Lee, Junhwan Kim +3
Despite the evolution of Convolutional Neural Networks (CNNs), their performance is surprisingly dependent on the choice of hyperparameters. However, it remains challenging to effi…
KoreALBERT: Pretraining a Lite BERT Model for Korean Language Understanding
Hyunjae Lee, Jaewoong Yoon, Bonggyu Hwang +3
A Lite BERT (ALBERT) has been introduced to scale up deep bidirectional representation learning for natural languages. Due to the lack of pretrained ALBERT models for Korean langua…
Reducing Domain Gap by Reducing Style Bias
Hyeonseob Nam, HyunJae Lee, Jongchan Park +2
Convolutional Neural Networks (CNNs) often fail to maintain their performance when they confront new test domains, which is known as the problem of domain shift. Recent studies sug…
SRM : A Style-based Recalibration Module for Convolutional Neural Networks
HyunJae Lee, Hyo-Eun Kim, Hyeonseob Nam
Following the advance of style transfer with Convolutional Neural Networks (CNNs), the role of styles in CNNs has drawn growing attention from a broader perspective. In this paper,…
Clear the Fog: Combat Value Assessment in Incomplete Information Games with Convolutional Encoder-Decoders
Hyungu Kahng, Yonghyun Jeong, Yoon Sang Cho +12
StarCraft, one of the most popular real-time strategy games, is a compelling environment for artificial intelligence research for both micro-level unit control and macro-level stra…