no code implementations • 19 Nov 2023 • Chengrui Gao, Ziyuan Yang, Min Zhu, Andrew Beng Jin Teoh
This paper proposes a scale-aware competitive network (SAC-Net), which includes the Inner-Scale Competition Module (ISCM) and the Across-Scale Competition Module (ASCM) to capture texture characteristics related to orientation and scale.
no code implementations • 18 Nov 2023 • Ziyuan Yang, Zerui Shao, Huijie Huangfu, Hui Yu, Andrew Beng Jin Teoh, Xiaoxiao Li, Hongming Shan, Yi Zhang
Federated learning (FL) is a promising distributed paradigm, eliminating the need for data sharing but facing challenges from data heterogeneity.
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)
1 code implementation • IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2023 • Ziyuan Yang, Huijie Huangfu, Lu Leng, Bob Zhang, Andrew Beng Jin Teoh, Yi Zhang
The traditional competition mechanism focuses solely on selecting the winner of different channels without considering the spatial information of the features.
1 code implementation • 1 Aug 2023 • Ziyuan Yang, Andrew Beng Jin Teoh, Bob Zhang, Lu Leng, Yi Zhang
Subsequently, we introduce anchor models for short- and long-spectrum, which constrain the optimization directions of local models associated with long- and short-spectrum images.
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 • 1 Oct 2022 • Timilehin B. Aderinola, Tee Connie, Thian Song Ong, Andrew Beng Jin Teoh, Michael Kah Ong Goh
This paper proposes a deep learning approach to extract age-associated features from model-based gait for age group classification.
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.
no code implementations • 9 Jun 2022 • Xingbo Dong, Zhihui Miao, Lan Ma, Jiajun Shen, Zhe Jin, Zhenhua Guo, Andrew Beng Jin Teoh
Yet, the security and privacy of the extracted features from deep learning models (deep features) have been often overlooked.
1 code implementation • 29 May 2022 • Leslie Ching Ow Tiong, Dick Sigmund, Andrew Beng Jin Teoh
Recently, the transformer model has been successfully employed for the multi-view 3D reconstruction problem.
1 code implementation • CVPR 2022 • Xingbo Dong, Wanyan Xu, Zhihui Miao, Lan Ma, Chao Zhang, Jiewen Yang, Zhe Jin, Andrew Beng Jin Teoh, Jiajun Shen
Next, a fully convolutional network is proposed to achieve the low-light image enhancement by fusing colored raw data with synthesized monochrome raw data.
1 code implementation • 11 Jun 2021 • Guang Hua, Andrew Beng Jin Teoh, Haijian Zhang
The constant Q transform (CQT) has been shown to be one of the most effective speech signal pre-transforms to facilitate synthetic speech detection, followed by either hand-crafted (subband) constant Q cepstral coefficient (CQCC) feature extraction and a back-end binary classifier, or a deep neural network (DNN) directly for further feature extraction and classification.
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.
1 code implementation • 18 Feb 2019 • Leslie Ching Ow Tiong, Andrew Beng Jin Teoh, Yunli Lee
We also introduce and share a new dataset for periocular in the wild, namely Ethnic-ocular dataset for benchmarking.
no code implementations • 28 Sep 2018 • Yen-Lung Lai, Jung-Yeon Hwang, Zhe Jin, Soohyong Kim, Sangrae Cho, Andrew Beng Jin Teoh
In this paper, we propose a novel biometric cryptosystem for vectorial biometrics named symmetric keyring encryption (SKE) inspired by Rivest's keyring model (2016).
no code implementations • 16 Mar 2017 • Zhe Jin, Yen-Lung Lai, Jung-Yeon Hwang, Soo-Hyung Kim, Andrew Beng Jin Teoh
In this paper, we propose a ranking based locality sensitive hashing inspired two-factor cancelable biometrics, dubbed "Index-of-Max" (IoM) hashing for biometric template protection.
no code implementations • 23 Jul 2016 • Zhe Jin, Yen-Lung Lai, Andrew Beng Jin Teoh
The former takes care of the accuracy performance mitigating numeric noises/perturbations while the latter offers strong non-invertible transformation via nonlinear feature embedding from Euclidean to Rank space that leads to toughness in inversion.
no code implementations • 24 Apr 2016 • Cheng Yaw Low, Andrew Beng Jin Teoh, Cong Jie Ng
The 2-FFC of Gabor, PCA and ICA filters thus yields three offspring sets: (1) Gabor filters solely, (2) Gabor-PCA filters, and (3) Gabor-ICA filters, to render the learning-free and the learning-based 2-FFC descriptors.
no code implementations • 8 Jul 2015 • Cong Jie Ng, Andrew Beng Jin Teoh
In this paper, we proposed a data-independence network, dubbed DCTNet for face recognition in which we adopt Discrete Cosine Transform (DCT) as filter banks in place of PCA.