Towards Robust Person Re-Identification by Adversarial Training with Dynamic Attack Strategy

J Wei, C Pan, S He, G Wang, Y Yang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Recently, person re-identification has gained significant attention from both academic and
industry fields due to its potential applications in surveillance and security. However, the …

[PDF][PDF] Literature Review: Adversarial Training of Deep Neural Networks

D Korth - danielkorth.io
Deep neural networks are susceptible to adversarial examples; small and imperceptible
changes made to the input that can completely alter the prediction of the model. To make …