Generalizing to unseen domains: A survey on domain generalization

J Wang, C Lan, C Liu, Y Ouyang, T Qin… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Machine learning systems generally assume that the training and testing distributions are
the same. To this end, a key requirement is to develop models that can generalize to unseen …

Racial bias within face recognition: A survey

S Yucer, F Tektas, N Al Moubayed… - ACM Computing Surveys, 2023 - dl.acm.org
Facial recognition is one of the most academically studied and industrially developed areas
within computer vision where we readily find associated applications deployed globally. This …

Do different tracking tasks require different appearance models?

Z Wang, H Zhao, YL Li, S Wang… - Advances in Neural …, 2021 - proceedings.neurips.cc
Tracking objects of interest in a video is one of the most popular and widely applicable
problems in computer vision. However, with the years, a Cambrian explosion of use cases …

Visual-to-EEG cross-modal knowledge distillation for continuous emotion recognition

S Zhang, C Tang, C Guan - Pattern Recognition, 2022 - Elsevier
Visual modality is one of the most dominant modalities for current continuous emotion
recognition methods. Compared to which the EEG modality is relatively less sound due to its …

On generalizing beyond domains in cross-domain continual learning

C Simon, M Faraki, YH Tsai, X Yu… - Proceedings of the …, 2022 - openaccess.thecvf.com
In the real world, humans have the ability to accumulate new knowledge in any conditions.
However, deeplearning suffers from the phenomenon so-called catastrophic forgetting of the …

A survey of face recognition

X Wang, J Peng, S Zhang, B Chen, Y Wang… - arXiv preprint arXiv …, 2022 - arxiv.org
Recent years witnessed the breakthrough of face recognition with deep convolutional neural
networks. Dozens of papers in the field of FR are published every year. Some of them were …

Enhancing adversarial robustness for deep metric learning

M Zhou, VM Patel - … of the IEEE/CVF Conference on …, 2022 - openaccess.thecvf.com
Owing to security implications of adversarial vulnerability, adversarial robustness of deep
metric learning models has to be improved. In order to avoid model collapse due to …

Attention-based dynamic alignment and dynamic distribution adaptation for remote sensing cross-domain scene classification

C Yang, Y Dong, B Du, L Zhang - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Due to the lack of high-quality labeled data and poor generalization ability of supervised
models in remote sensing scene classification, cross-domain scene classification is …

{FACE-AUDITOR}: Data Auditing in Facial Recognition Systems

M Chen, Z Zhang, T Wang, M Backes… - 32nd USENIX Security …, 2023 - usenix.org
Few-shot-based facial recognition systems have gained increasing attention due to their
scalability and ability to work with a few face images during the model deployment phase …

Learning to learn across diverse data biases in deep face recognition

C Liu, X Yu, YH Tsai, M Faraki… - Proceedings of the …, 2022 - openaccess.thecvf.com
Abstract Convolutional Neural Networks have achieved remarkable success in face
recognition, in part due to the abundant availability of data. However, the data used for …