Decoupled mixup for out-of-distribution visual recognition

H Liu, W Zhang, J Xie, H Wu, B Li, Z Zhang, Y Li… - … on Computer Vision, 2022 - Springer
Convolutional neural networks (CNN) have demonstrated remarkable performance, when
the training and testing data are from the same distribution. However, such trained CNN …

Taming self-supervised learning for presentation attack detection: De-folding and de-mixing

Z Kong, W Zhang, F Liu, W Luo, H Liu… - … on Neural Networks …, 2023 - ieeexplore.ieee.org
Biometric systems are vulnerable to presentation attacks (PAs) performed using various PA
instruments (PAIs). Even though there are numerous PA detection (PAD) techniques based …

Activation Template Matching Loss for Explainable Face Recognition

H Lin, H Liu, Q Li, L Shen - 2023 IEEE 17th International …, 2023 - ieeexplore.ieee.org
Can we construct an explainable face recognition network able to learn a facial part-based
feature like eyes, nose, mouth and so forth, without any manual annotation or additionalsion …

Decoupled Mixup for Generalized Visual Recognition

H Liu, W Zhang, J Xie, H Wu, B Li, Z Zhang, Y Li… - arXiv preprint arXiv …, 2022 - arxiv.org
Convolutional neural networks (CNN) have demonstrated remarkable performance when
the training and testing data are from the same distribution. However, such trained CNN …