no code implementations • 6 Dec 2023 • Sangwoong Yoon, Dohyun Kwon, Himchan Hwang, Yung-Kyun Noh, Frank C. Park
We present Generalized Contrastive Divergence (GCD), a novel objective function for training an energy-based model (EBM) and a sampler simultaneously.
1 code implementation • 20 Aug 2022 • Sangwoong Yoon, Jinwon Choi, Yonghyeon LEE, Yung-Kyun Noh, Frank Chongwoo Park
A reliable evaluation method is essential for building a robust out-of-distribution (OOD) detector.
no code implementations • ICLR 2022 • Yonghyeon LEE, Sangwoong Yoon, MinJun Son, Frank C. Park
The recent success of autoencoders for representation learning can be traced in large part to the addition of a regularization term.
no code implementations • 29 Sep 2021 • Sangwoong Yoon, Jinwon Choi, Yonghyeon LEE, Yung-Kyun Noh, Frank C. Park
As an outlier may deviate from the training distribution in unexpected ways, an ideal OOD detector should be able to detect all types of outliers.
2 code implementations • 12 May 2021 • Sangwoong Yoon, Yung-Kyun Noh, Frank Chongwoo Park
The specific role of the normalization constraint is to ensure that the out-of-distribution (OOD) regime has a small likelihood when samples are learned using maximum likelihood.
no code implementations • 1 Jan 2021 • Kyoung-Woon On, Eun-Sol Kim, Il-Jae Kwon, Sangwoong Yoon, Byoung-Tak Zhang
To further investigate the effectiveness of our proposed method, we evaluate our approach on a real-world problem, image retrieval with visual scene graphs.
no code implementations • 1 Jan 2021 • Sangwoong Yoon, Yung-Kyun Noh, Frank C. Park
This phenomenon, which we refer to as outlier reconstruction, has a detrimental effect on the use of autoencoders for outlier detection, as an autoencoder will misclassify a clear outlier as being in-distribution.
1 code implementation • 29 Dec 2020 • Sangwoong Yoon, Woo Young Kang, Sungwook Jeon, SeongEun Lee, Changjin Han, Jonghun Park, Eun-Sol Kim
Based on this idea, we propose a novel approach for image-to-image retrieval using scene graph similarity measured by graph neural networks.