no code implementations • 19 Feb 2024 • Leo Hyun Park, JaeUk Kim, Myung Gyo Oh, Jaewoo Park, Taekyoung Kwon
Deep learning models continue to advance in accuracy, yet they remain vulnerable to adversarial attacks, which often lead to the misclassification of adversarial examples.
no code implementations • 29 Jan 2024 • Jaewoo Park, Jaeguk Kim, Nam Ik Cho
Accurately estimating the pose of an object is a crucial task in computer vision and robotics.
no code implementations • ICCV 2023 • Jaewoo Park, Jacky Chen Long Chai, Jaeho Yoon, Andrew Beng Jin Teoh
(3) The conventional feature norm fails to capture the deactivation tendency of hidden layer neurons, which may lead to misidentification of ID samples as OOD instances.
2 code implementations • 26 Sep 2023 • Jaewoo Park, Yoon Gyo Jung, Andrew Beng Jin Teoh
Detecting out-of-distribution (OOD) samples are crucial for machine learning models deployed in open-world environments.
Ranked #1 on Out-of-Distribution Detection on ImageNet-1k vs Curated OODs (avg.) (using extra training data)
no code implementations • 17 Aug 2023 • Jaewoo Park, Chenghao Quan, Hyungon Moon, Jongeun Lee
In this paper we show hyperdimensional computing can be a rescue for privacy-preserving machine learning over encrypted data.
no code implementations • CVPR 2023 • Jacky Chen Long Chai, Tiong-Sik Ng, Cheng-Yaw Low, Jaewoo Park, Andrew Beng Jin Teoh
Very low-resolution face recognition (VLRFR) poses unique challenges, such as tiny regions of interest and poor resolution due to extreme standoff distance or wide viewing angle of the acquisition devices.
1 code implementation • 5 Jan 2023 • Hojin Park, Jaewoo Park, Andrew Beng Jin Teoh
In this paper, we focus on addressing the open-set face identification problem on a few-shot gallery by fine-tuning.
no code implementations • 23 Sep 2022 • Jaewoo Park, Hojin Park, Eunju Jeong, Andrew Beng Jin Teoh
Overall, the discrepancy in the Jacobian norm between the known and unknown classes enables OSR.
1 code implementation • 4 Aug 2022 • Chaeyoon Jeong, Sundong Kim, Jaewoo Park, Yeonsoo Choi
Given the huge volume of cross-border flows, effective and efficient control of trade becomes more crucial in protecting people and society from illicit trade.
1 code implementation • 16 Dec 2021 • Jaewoo Park, Nam Ik Cho
Our pose estimation method, dynamic projective spatial transformer network (DProST), localizes the region of interest grid on the rays in camera space and transforms the grid to object space by estimated pose.
no code implementations • 29 Sep 2021 • Faaiz Asim, Jaewoo Park, Azat Azamat, Jongeun Lee
We show that this asymmetry in the number of positive and negative quantization levels can result in significant quantization error and performance degradation at low precision.
no code implementations • 12 Dec 2020 • Yoon Gyo Jung, Jaewoo Park, Cheng Yaw Low, Jacky Chen Long Chai, Leslie Ching Ow Tiong, Andrew Beng Jin Teoh
Overall, CKD empowers the sole periocular network to produce robust discriminative embeddings for periocular recognition in the wild.
no code implementations • 3 Mar 2020 • Jaewoo Park, Yoon Gyo Jung, Andrew Beng Jin Teoh
In DCAE, (a) we force a compact latent space to bijectively represent the in-class data by reconstructing them through internal discriminative layers of generative adversarial nets.
no code implementations • 17 Oct 2019 • Xingbo Dong, Jaewoo Park, Zhe Jin, Andrew Beng Jin Teoh, Massimo Tistarelli, KokSheik Wong
Cancelable biometrics (CB) employs an irreversible transformation to convert the biometric features into transformed templates while preserving the relative distance between two templates for security and privacy protection.
no code implementations • 2 Mar 2019 • Uiwon Hwang, Jaewoo Park, Hyemi Jang, Sungroh Yoon, Nam Ik Cho
Deep neural networks are widely used and exhibit excellent performance in many areas.
Ranked #2 on Adversarial Defense against FGSM Attack on MNIST
1 code implementation • 17 Nov 2018 • Cheng-Yaw Low, Jaewoo Park, Andrew Beng-Jin Teoh
Stacking-based deep neural network (S-DNN) is aggregated with pluralities of basic learning modules, one after another, to synthesize a deep neural network (DNN) alternative for pattern classification.